Papers

Optimizing expensive to evaluate black-box functions over an input space consisting of all permutations of d objects is an important problem with many real-world applications. For example, placement of functional blocks in hardware design to optimize performance via simulations. The overall goal is to minimize the number of function evaluations to find high-performing permutations. The key challenge in solving this problem using the Bayesian optimization (BO) framework is to trade-off the complexity of statistical model and tractability of acquisition function optimization. In this paper, we propose and evaluate two algorithms for BO over Permutation Spaces (BOPS). First, BOPS-T employs Gaussian process (GP) surrogate model with Kendall kernels and a Tractable acquisition function optimization approach to select the sequence of permutations for evaluation. Second, BOPS-H employs GP surrogate model with Mallow kernels and a Heuristic search approach to optimize the acquisition function. We theoretically analyze the performance of BOPS-T to show that their regret grows sub-linearly. Our experiments on multiple synthetic and real-world benchmarks show that both BOPS-T and BOPS-H perform better than the state-of-the-art BO algorithm for combinatorial spaces. To drive future research on this important problem, we make new resources and real-world benchmarks available to the community.

poster session 2 @ blue 2, poster session 9 @ blue 2, oral session 9 @ blue 2, poster session 2, poster session 9, oral session 9

Image-based survival prediction models can facilitate doctors in diagnosing and treating cancer patients. With the advance of digital pathology technologies, the big whole slide images (WSIs) provide increasing resolution and more details for diagnosis. However, the gigabyte-size WSIs would make most models computationally infeasible. To this end, instead of using the complete WSIs, most of existing models only use a pre-selected subset of key patches or patch clusters as input, which might fail to completely capture the patient's tumor morphology. In this work, we aim to develop a novel survival analysis model to fully utilize the complete WSI information. We show that the use of a Vision Transformer (ViT) backbone, together with convolution operations involved in it, is an effective framework to improve the prediction performance. Additionally, we present a post-hoc explainable method to identify the most salient patches and distinct morphology features, making the model more faithful and the results easier to comprehend by human users. Evaluations on two large cancer datasets show that our proposed model is more effective and has better interpretability for survival prediction.

poster session 2 @ red 2, poster session 9 @ red 2, poster session 2, poster session 9

In this paper, based on an asymptotic analysis of the Softmax layer, we show that when training neural networks for classification tasks, the weight vectors corre sponding to each class of the Softmax layer tend to converge to the class-wise means computed at the representation layer (for specific choices of the representation activation). We further show some consequences of our findings to the context of transfer learning, essentially by proposing a simple yet effective initialization procedure that significantly accelerates the learning of the Softmax layer weights as the target domain gets closer to the source one. Experiments are notably performed on the datasets: MNIST, Fashion MNIST, Cifar10, and Cifar100 and using a standard CNN architecture.

poster session 2 @ blue 2, poster session 9 @ blue 2, poster session 2, poster session 9

Features, logits, and labels are the three primary data when a sample passes through a deep neural network. Feature perturbation and label perturbation receive increasing attention in recent years. They have been proven to be useful in various deep learning approaches. For example, (adversarial) feature perturbation can improve the robustness or even generalization capability of learned models. However, limited studies have explicitly explored for the perturbation of logit vectors. This work discusses several existing methods related to logit perturbation. Based on a unified viewpoint between positive/negative data augmentation and loss variations incurred by logit perturbation, a new method is proposed to explicitly learn to perturb logits. A comparative analysis is conducted for the perturbations used in our and existing methods. Extensive experiments on benchmark image classification data sets and their long-tail versions indicated the competitive performance of our learning method. In addition, existing methods can be further improved by utilizing our method.

poster session 2 @ red 2, poster session 9 @ red 2, poster session 2, poster session 9

With the rapid increase of multimedia data, a large body of literature has emerged to work on multimodal summarization, the majority of which target at refining salient information from textual and image modalities to output a pictorial summary with the most relevant images. Existing methods mostly focus on either extractive or abstractive summarization and rely on the presence and quality of image captions to build image references. We are the first to propose a Unified framework for Multimodal Summarization grounding on BART, UniMS, that integrates extractive and abstractive objectives, as well as selecting the image output. Specially, we adopt knowledge distillation from a vision-language pretrained model to improve image selection, which avoids any requirement on the existence and quality of image captions. Besides, we introduce a visual guided decoder to better integrate textual and visual modalities in guiding abstractive text generation. Results show that our best model achieves a new state-of-the-art result on a large-scale benchmark dataset. The newly involved extractive objective as well as the knowledge distillation technique are proven to bring a noticeable improvement to the multimodal summarization task.

poster session 6 @ red 5, poster session 9 @ red 5, poster session 6, poster session 9

In the online (time-series) search problem, a player is presented with a sequence of prices which are revealed in an online manner. In the standard definition of the problem, for each revealed price, the player must decide irrevocably whether to accept or reject it, without knowledge of future prices (other than an upper and a lower bound on their extreme values), and the objective is to minimize the competitive ratio, namely the worst case ratio between the maximum price in the sequence and the one selected by the player. The problem formulates several applications of decision-making in the face of uncertainty on the revealed samples. Previous work on this problem has largely assumed extreme scenarios in which either the player has almost no information about the input, or the player is provided with some powerful, and error-free advice. In this work, we study learning-augmented algorithms, in which there is a potentially erroneous prediction concerning the input. Specifically, we consider two different settings: the setting in which the prediction is related to the maximum price in the sequence, as well as well as the setting in which the prediction is obtained as a response to a number of binary queries. For both settings, we provide tight, or near-tight upper and lower bounds on the worst-case performance of search algorithms as a function of the prediction error. We also provide experimental results on data obtained from stock exchange markets that confirm the theoretical analysis, and explain how our techniques can be applicable to other learning-augmented applications.

poster session 2 @ blue 1, poster session 9 @ blue 1, oral session 9 @ blue 1, poster session 2, poster session 9, oral session 9

Formal response organizations perform rapid damage assessments after natural and human-induced disasters to measure the extent of damage to infrastructures such as roads, bridges, and buildings. This time-critical task, when performed using traditional approaches such as experts surveying the disaster areas, poses serious challenges and delays response. This paper presents an AI-based system that leverages citizen science to collect damage images reported on social media and perform rapid damage assessment in real-time. Several image processing models in the system tackle non-trivial challenges posed by social media as a data source, such as high-volume of redundant and irrelevant content. The system determines the severity of damage using a state-of-the-art computer vision model. Together with a response organization in the US, we deployed the system to identify damage reports during a major real-world disaster. We observe that almost 42% of the images are unique, 28% relevant, and more importantly, only 10% of them contain either mild or severe damage. Experts from our partner organization provided feedback on the system's mistakes, which we used to perform additional experiments to retrain the models. Consequently, the retrained models based on expert feedback on the target domain data helped us achieve significant performance improvements.

poster session 9 @ red 6, poster session 7 @ red 6, poster session 9, poster session 7

Heterogeneous Graph Neural Networks (HGNNs) have drawn increasing attention in recent years and achieved outstanding performance in many tasks. However, despite their wide use, there is currently no understanding of their robustness to adversarial attacks. In this work, we first systematically study the robustness of HGNNs and show that they can be easily fooled by adding the adversarial edge between the target node and large-degree node (i.e., hub). Furthermore, we show two key reasons for such vulnerability of HGNNs: one is perturbation enlargement effect, i.e., HGNNs, failing to encode transiting probability, will enlarge the effect of the adversarial hub in comparison of GCNs, and the other is soft attention mechanism, i.e., such mechanism assigns positive attention values to obviously unreliable neighbors. Based on the two facts, we propose a novel robust HGNN framework \textit{RoHe} against topology adversarial attacks by equipping an attention purifier, which can prune malicious neighbors based on topology and feature. Specifically, to eliminate the perturbation enlargement, we introduce the metapath-based transiting probability as the prior criterion of the purifier, restraining the confidence of malicious neighbors from the adversarial hub. Then the purifier learns to mask out neighbors with low confidence, thus can effectively alleviate the negative effect of malicious neighbors in the soft attention mechanism. Extensive experiments on different benchmark datasets for multiple HGNNs are conducted, where the considerable improvement of HGNNs under adversarial attacks will demonstrate the effectiveness and generalization ability of our defense framework.

poster session 5 @ blue 5, poster session 9 @ blue 5, poster session 5, poster session 9

Effective communication can improve coordination in cooperative multi-agent reinforcement learning (MARL). One popular communication scheme is exchanging agents' local observations or latent embeddings and using them to augment individual local policy input. Such a communication paradigm can reduce uncertainty for local decision-making and induce implicit coordination. However, it enlarges agents' local policy spaces and increases learning complexity, leading to poor coordination in complex settings. To handle this limitation, this paper proposes a novel framework named Multi-Agent Incentive Communication (MAIC) that allows each agent to learn to generate incentive messages and bias other agents' value functions directly, resulting in effective explicit coordination. Our method firstly learns targeted teammate models, with which each agent can anticipate the teammate's action selection and generate tailored messages to specific agents. We further introduce a novel regularization to leverage interaction sparsity and improve communication efficiency. MAIC is agnostic to specific MARL algorithms and can be flexibly integrated with different value function factorization methods. Empirical results demonstrate that our method significantly outperforms baselines and achieves excellent performance on multiple cooperative MARL tasks.

poster session 4 @ blue 6, poster session 9 @ blue 6, poster session 4, poster session 9

We focus on the confounding bias between language and location in the visual grounding pipeline, where we find that the bias is the major visual reasoning bottleneck. For example, the grounding process is usually a trivial languagelocation association without visual reasoning, e.g., grounding any language query containing sheep to the nearly central regions, due to that most queries about sheep have groundtruth locations at the image center. First, we frame the visual grounding pipeline into a causal graph, which shows the causalities among image, query, target location and underlying confounder. Through the causal graph, we know how to break the grounding bottleneck: deconfounded visual grounding. Second, to tackle the challenge that the confounder is unobserved in general, we propose a confounder-agnostic approach called: Referring Expression Deconfounder (RED), to remove the confounding bias. Third, we implement RED as a simple language attention, which can be applied in any grounding method. On popular benchmarks, RED improves various state-of-the-art grounding methods by a significant margin. Codes are available in Appendix.

poster session 2 @ red 4, poster session 9 @ red 4, oral session 9 @ red 4, poster session 2, poster session 9, oral session 9

Inferring the causal structure of a set of random variables is a crucial problem in many disciplines of science. Over the past two decades, various approaches have been pro- posed for causal discovery from observational data. How- ever, most of the existing methods are designed for either purely discrete or continuous data, which limit their practical usage. In this paper, we target the problem of causal structure learning from observational mixed-type data. Although there are a few methods that are able to handle mixed-type data, they suffer from restrictions, such as linear assumption and poor scalability. To overcome these weaknesses, we formulate the causal mechanisms via mixed structure equation model and prove its identifiability under mild conditions. A novel locally consistent score, named CVMIC, is proposed for causal directed acyclic graph (DAG) structure learning. Moreover, we propose an efficient conditional independence test, named MRCIT, for mixed-type data, which is used in causal skeleton learning and final pruning to further improve the computational efficiency and precision of our model. Experimental results on both synthetic and real-world data demonstrate that our proposed hybrid model outperforms the other state-of-the-art methods. Our source code is available at https://github.com/DAMO-DI-ML/AAAI2022-HCM.

poster session 4 @ blue 3, poster session 9 @ blue 3, poster session 4, poster session 9

By interpreting Graph Neural Networks (GNNs) as the message passing from the spatial perspective, their success is attributed to Laplacian smoothing. However, it also leads to serious over-smoothing issue by stacking many layers. Recently, many efforts have been paid to overcome this issue in semi-supervised learning. Unfortunately, it is more serious in unsupervised node representation learning task due to the lack of supervision information. Thus, most of the unsupervised or self-supervised GNNs often employ \textit{one-layer GCN} as the encoder. Essentially, the over-smoothing issue is caused by the over-simplification of the existing message passing, which possesses two intrinsic limits: blind message and uniform passing. In this paper, a novel Diverse and Interactive Message Passing (DIMP) is proposed for self-supervised learning by overcoming these limits. Firstly, to prevent the message from blindness and make it interactive between two connected nodes, the message is determined by both the two connected nodes instead of the attributes of one node. Secondly, to prevent the passing from uniformness and make it diverse over different attribute channels, different propagation weights are assigned to different elements in the message. To this end, a natural implementation of the message in DIMP is the element-wise product of the representations of two connected nodes. From the perspective of numerical optimization, the proposed DIMP is equivalent to performing an overlapping community detection via expectation-maximization (EM). Both the objective function of the community detection and the convergence of EM algorithm guarantee that DMIP can prevent from over-smoothing issue. Extensive evaluations on node-level and graph-level tasks demonstrate the superiority of DIMP on improving performance and overcoming over-smoothing issue.

poster session 5 @ blue 5, poster session 9 @ blue 5, poster session 5, poster session 9

Handwritten mathematical expression recognition aims to automatically generate LaTeX sequences from given images. Currently, attention-based encoder-decoder models are widely used in this task. They typically generate target sequences in a left-to-right (L2R) manner, leaving the right-to-left (R2L) contexts unexploited. In this paper, we propose an Attention aggregation based Bi-directional Mutual learning Network (ABM) which consists of one shared encoder and two parallel inverse decoders (L2R and R2L). The two decoders are enhanced via mutual distillation, which involves one-to-one knowledge transfer at each training step, making full use of the complementary information from two inverse directions. Moreover, in order to deal with mathematical symbols in diverse scales, an Attention Aggregation Module (AAM) is proposed to effectively integrate multi-scale coverage attentions. Notably, in the inference phase, given that the model already learns knowledge from two inverse directions, we only use the L2R branch for inference, keeping the original parameter size and inference speed. Extensive experiments demonstrate that our proposed approach achieves the recognition accuracy of 56.85 % on CROHME 2014, 52.92 % on CROHME 2016, and 53.96 % on CROHME 2019 without data augmentation and model ensembling, substantially outperforming the state-of-the-art methods. The source code is available in the supplementary materials.

poster session 2 @ red 4, poster session 9 @ red 4, oral session 9 @ red 4, poster session 2, poster session 9, oral session 9

Temporal sentence grounding (TSG) is crucial and fundamental for video understanding. Although existing methods train well-designed deep networks with large amount of data, we find that they can easily forget the rarely appeared cases during training due to the off-balance data distribution, which influences the model generalization and leads to unsatisfactory performance. To tackle this issue, we propose a memory-augmented network, called Memory-Guided Semantic Learning Network (MGSL-Net), that learns and memorizes the rarely appeared content in TSG task. Specifically, our proposed model consists of three main parts: cross-modal interaction module, memory augmentation module, and heterogeneous attention module. We first align the given video-query pair by a cross-modal graph convolutional network, and then utilize memory module to record the cross-modal shared semantic features in the domain-specific persistent memory. During training, the memory slots are dynamically associated with both common and rare cases, alleviating the forgetting issue. In testing, the rare cases can thus be enhanced by retrieving the stored memories, leading to better generalization. At last, the heterogeneous attention module is utilized to integrate the enhanced multi-modal features in both video and query domains. Experimental results on three benchmarks show the superiority of our method on both effectiveness and efficiency, which substantially improves the accuracy not only on the entire dataset but also on the rare cases.

poster session 2 @ red 4, poster session 9 @ red 4, poster session 2, poster session 9

Cognitive processing signals can be used to improve natural language processing (NLP) tasks. However, it is not clear how these signals correlate with linguistic information. Bridging between human language processing and linguistic features has been widely studied in neurolinguistics, usually via single-variable controlled experiments with highly-controlled stimuli. Such methods not only compromises the authenticity of natural reading, but also are time-consuming and expensive. In this paper, we propose a data-driven method to investigate the relationship between cognitive processing signals and linguistic features. Specifically, we present a unified attentional framework that is composed of embedding, attention, encoding and predicting layers to selectively map cognitive processing signals to linguistic features. We define the mapping procedure as a bridging task and develop 12 bridging tasks for lexical, syntactic and semantic features. The proposed framework only requires cognitive processing signals recorded under natural reading as inputs, and can be used to detect a wide range of linguistic features with a single cognitive dataset. Observations from experiment results resonate with previous neuroscience findings. In addition to this, our experiments also reveal a number of interesting findings, such as the correlation between contextual eye-tracking features and tense of sentence.

poster session 2 @ red 2, poster session 9 @ red 2, poster session 2, poster session 9

Temporal grounding aims to localize a video moment which is semantically aligned with a given natural language query. Existing methods typically apply a detection or regression pipeline on the fused representation with the research focus on designing complicated prediction heads or fusion strategies. Instead, from a perspective on temporal grounding as a metric-learning problem, we present a Mutual Matching Network (MMN), to directly model the similarity between language queries and video moments in a joint embedding space. This new metric-learning framework enables fully exploiting negative samples from two new aspects: constructing negative cross-modal pairs in a mutual matching scheme and mining negative pairs across different videos. These new negative samples could enhance the joint representation learning of two modalities via cross-modal mutual matching to maximize their mutual information. Experiments show that our MMN achieves highly competitive performance compared with the state-of-the-art methods on four video grounding benchmarks. Based on MMN, we present a winner solution for the HC-STVG challenge of the 3rd PIC workshop. This suggests that metric learning is still a promising method for temporal grounding via capturing the essential cross-modal correlation in a joint embedding space. Code is available at https://github.com/MCG-NJU/MMN.

poster session 5 @ red 1, poster session 9 @ red 1, poster session 5, poster session 9

A weak backdoor, or simply a backdoor, for a Boolean SAT formula F into a class of SAT formulae C is a partial truth assignment T such that F[T] is in C and satisfiability is preserved. The problem of finding a backdoor from class C1 into class C2, or WB(C1,C2), can be stated as follows: Given a formula F in C1, and a natural number k, determine whether there exists a backdoor for F into C2 assigning at most k variables. The class 0-Val contains all Boolean formulae with at least one negative literal in each clause. We design a new algorithm for WB(3CNF, 0-Val) by reducing it to a local search variant of 3-SAT. We show that our algorithm runs in time O*(2.562^k), improving on the previous state-of-the-art of O*(2.85^k). Here, the O* notation is a variant of the big-O notation that allows to omit polynomial factors in the input size. Next, we look at WB(3CNF, Null), where Null is the class consisting of the empty formula. This problem was known to have a trivial running time upper bound of O*(6^k) and can easily be solved in O*(3^k) time. We use a reduction to Conflict-Free-d-Hitting-Set to prove an upper bound of O*(2.2738^k), and also prove a lower bound of 2^o(k) assuming the Exponential Time Hypothesis. Finally, Horn is the class of formulae with at most one positive literal per clause. We improve the previous O*(4.54^k) running time for WB(3CNF, Horn) problem to O*(4.17^k), by exploiting the structure of the SAT instance to give a novel proof of the non-existence of the slowest cases after a slight restructuring of the branching priorities.

poster session 2 @ blue 4, poster session 9 @ blue 4, poster session 2, poster session 9

This paper studies defender patrol deception in general Stackelberg security games (SSGs), where a defender attempts to alter the attacker's perception of the defender's patrolling intensity so as to influence the attacker's decision making. We are interested in understanding the complexity and effectiveness of optimal defender deception under different attacker behavior models. Specifically, we consider three different attacker strategies of response (to the defender's deception) with increasing sophistication, and design efficient polynomial-time algorithms to compute the equilibrium for each. Moreover, we prove formal separation for the effectiveness of patrol deception when facing an attacker of increasing sophistication, until it becomes even harmful to the defender when facing the most intelligent attacker we consider. Our results shed light on when and how deception should be used in SSGs. We conduct extensive experiments to illustrate our theoretical results in various game settings.

poster session 4 @ blue 6, poster session 9 @ blue 6, poster session 4, poster session 9

Deep neural networks are vulnerable to small input perturbations known as adversarial attacks. Inspired by the fact that these adversaries are constructed by iteratively minimizing the confidence of a network for the true class label, we propose the anti-adversary layer, aimed at countering this effect. In particular, our layer generates an input perturbation in the opposite direction of the adversarial one and feeds the classifier a perturbed version of the input. Our approach is training-free and theoretically supported. We verify the effectiveness of our approach by combining our layer with both nominally and robustly trained models and conduct large-scale experiments from black-box to adaptive attacks on CIFAR10, CIFAR100, and ImageNet. Our layer significantly enhances model robustness while coming at no cost on clean accuracy.

poster session 4 @ blue 6, poster session 9 @ blue 6, poster session 4, poster session 9

Multiple medical institutions collaboratively training a model using federated learning (FL) has become a promising solution for maximizing the potential of data-driven models, yet the non-independent and identically distributed (non-iid) data in medical images is still an outstanding challenge in real-world practice. The feature heterogeneity caused by diverse scanners or sensors introduces a drift in the learning process, in both local (client) and global (server) optimizations, which harms the convergence as well as model performance. Many previous works have attempted to address the non-iid issue by tackling the drift locally or globally, but how to jointly solve the two essentially coupled drifts is still unclear. In this work, we concentrate on handling both local and global drifts and introduce a new harmonizing framework called HarmoFL. First, we propose to mitigate the local update drift by normalizing amplitudes of images transformed into the frequency domain to mimic a unified scanner/sensor, in order to generate a harmonized feature space across local clients. Second, based on harmonized features, we design a client weight perturbation guiding each local model to reach a flat optimum, where a neighborhood area of the local optimal solution has a uniformly low loss. Without any extra communication cost, the perturbation assists the global model to optimize towards a converged optimal solution by aggregating several local flat optima. We have theoretically analyzed the proposed method and empirically conducted extensive experiments on three medical image classification and segmentation tasks, showing that HarmoFL outperforms a set of recent state-of-the-art methods with promising convergence behavior.

poster session 2 @ red 2, poster session 9 @ red 2, poster session 2, poster session 9

Bottom-up knowledge compilation is a paradigm for generating representations of functions by iteratively conjoining constraints using a so-called apply function. When the input is not efficiently compilable into a language - generally a class of circuits - because optimal compiled representations are provably large, the problem is not the compilation algorithm as much as the choice of a language too restrictive for the input. In contrast, in this paper, we look at CNF formulas for which very small circuits exists and look at the efficiency of their bottom-up compilation in one of the most general languages, namely that of structured decomposable negation normal forms (str-DNNF). We prove that, while the inputs have constant size representations as str-DNNF, any bottom-up compilation in the general setting where conjunction and structure modification are allowed takes exponential time and space, since large intermediate results have to be produced. This unconditionally proves that the inefficiency of bottom-up compilation resides in the bottom-up paradigm itself.

poster session 2 @ red 4, poster session 9 @ red 4, poster session 2, poster session 9

Most economic reports suggest that almost half of the market value unlocked by artificial intelligence (AI) by the next decade (about 9 trillion USD per year) will be in marketing&sales. In particular, AI will allow the optimization of more and more intricate economic settings in which multiple different activities can be automated jointly. A relatively recent example is that one of ad auctions in which similar products or services are displayed together with their price, thus merging advertising and pricing in a unique website. This is the case, e.g., of Google Hotel Ads and TripAdvisor. More precisely, as in a classical ad auction, the ranking of the ads depends on the advertisers' bids, while, differently from classical ad auctions, the price is displayed together with the ad, so as to provide a direct comparison among the prices and thus dramatically affect the behavior of the users. This paper investigates how displaying prices and ads together conditions the properties of the main economic mechanisms such as VCG and GSP. Initially, we focus on the direct-revelation mechanism, showing that prices are chosen by the mechanisms once given the advertisers' reports. We also provide an efficient algorithm to compute the optimal allocation given the private information reported by the advertisers. Then, with both VCG and GSP payments, we show the inefficiency in terms of Price of Anarchy (PoA) and Stability (PoS) over the social welfare and mechanism's revenue when the advertisers choose the prices. The main results show that, with both VCG and GSP, PoS over the revenue may be unbounded even with two slots, while PoA over the social welfare may be as large as the number of slots. Finally, we show that, under some assumptions, simple modifications to VCG and GSP allow us to obtain a better PoS over the revenue.

poster session 4 @ blue 6, poster session 9 @ blue 6, oral session 4 @ blue 6, poster session 4, poster session 9, oral session 4

While self-training achieves state-of-the-art results in semi-supervised object detection (SSOD), it severely suffers from foreground-background and foreground-foreground imbalances in SSOD. In this paper, we propose an Adaptive Class-Rebalancing Self-Training (ACRST) with a novel memory module called CropBank to alleviate these imbalances and generate unbiased pseudo-labels. Besides, we observe that both self-training and data-rebalancing procedures suffer from noisy pseudo-labels in SSOD. Therefore, we contribute a simple yet effective two-stage pseudo-label filtering scheme to obtain accurate supervision. Our method achieves competitive performance on MS-COCO and VOC benchmarks. When using only 1% labeled data of MS-COCO, our method achieves 17.02 mAP improvement over the supervised method and 5.32 mAP gains compared with state-of-the-arts.

poster session 2 @ blue 2, poster session 9 @ blue 2, oral session 2 @ blue 2, poster session 2, poster session 9, oral session 2

Accelerated gradient methods are the cornerstones of large-scale, data-driven optimization problems that arise naturally in machine learning and other fields concerning data analysis. We introduce a gradient-based optimization framework for achieving acceleration, based on the recently introduced notion of fixed-time stability of dynamical systems. The method presents itself as a generalization of simple gradient-based methods suitably scaled to achieve convergence to the optimizer in a fixed-time, independent of the initialization. We achieve this by first leveraging a continuous-time framework for designing fixed-time stable dynamical systems, and later providing a consistent discretization strategy, such that the equivalent discrete-time algorithm tracks the optimizer in a practically fixed number of iterations. We also provide a theoretical analysis of the convergence behavior of the proposed gradient flows, and their robustness to additive disturbances for a range of functions obeying strong convexity, strict convexity, and possibly nonconvexity but satisfying the Polyak-Łojasiewicz inequality. We also show that the regret bound on the convergence rate is constant by virtue of the fixed-time convergence. The hyperparameters have intuitive interpretations and can be tuned to fit the requirements on the desired convergence rates. We validate the accelerated convergence properties of the proposed schemes on a range of numerical examples against the state-of-the-art optimization algorithms. Our work provides insights on developing novel optimization algorithms via discretization of continuous-time flows.

poster session 4 @ blue 3, poster session 9 @ blue 3, poster session 4, poster session 9

Optimal Transport (OT) has become a popular tool in machine learning to align finite datasets typically lying in the same vector space. To expand the range of possible applications, Co-Optimal Transport (Co-OT) jointly estimates two distinct transport plans, one for the rows (points) and one for the columns (features), to match two data matrices that might use different features. On the other hand, Gromov Wasserstein (GW) looks for a single transport plan from two pairwise intra-domain distance matrices. Both Co-OT and GW can be seen as specific extensions of OT to more complex data. In this paper, we propose a unified framework, called Optimal Tensor Transport (OTT), which takes the form of a generic formulation that encompasses OT, GW and Co-OT and can handle tensors of any order by learning possibly multiple transport plans. We derive theoretical results for the resulting new distance and present an efficient way for computing it. We further illustrate the interest of such a formulation in Domain Adaptation and Comparison-based Clustering.

poster session 4 @ blue 6, poster session 9 @ blue 6, poster session 4, poster session 9

NLP applications for code-mixed (CM) or mix-lingual text have gained a significant momentum recently, the main reason being the prevalence of language mixing in social media communications in multi-lingual societies like India, Mexico, Europe, parts of USA etc. Word embeddings are basic building blocks of any NLP system today, yet, word embedding for CM languages is an unexplored territory. The major bottleneck for CM word embeddings is switching points, where the language switches. These locations lack in contextually and statistical systems fail to model this phenomena due to high variance in the seen examples. In this paper we present our initial observations on applying switching point based positional encoding techniques for CM language, specifically Hinglish (Hindi - English). Results are only marginally better than SOTA, but it is evident that positional encoding could be an effective way to train position sensitive language models for CM text.

poster session 5 @ blue 5, poster session 9 @ blue 5, poster session 5, poster session 9

The quantal response (QR) model is widely used in Stackelberg security games (SSG) to model a bounded rational adversary. The QR model is a model of human response from among a large variety of prominent models known as discrete choice models. QR is the simplest type of discrete choice models and does not capture commonly observed phenomenon such as correlation among choices. We introduce the nested QR adversary model (based on nested logit model in discrete choice theory) in SSG which addresses shortcoming of the QR model. We present tractable approximation of the resulting equilibrium problem with nested QR adversary. We do so by deriving an interesting property of the equilibrium problem, namely a loosely coupled split into nested problems that mirrors the nested decision making by the adversary in the nested QR model. We show that each separate nested problem can be approximated efficiently and that the loosely coupled overall problem can be solved approximately by formulating it as a discretized version of a continuous dynamic program. Finally, we conduct experiments that show the scalability and parallelizability of our approach, as well as advantages of the nested QR model.

poster session 4 @ blue 6, poster session 9 @ blue 6, poster session 4, poster session 9

Model transparency is a prerequisite in many domains and an increasingly popular area in machine learning research. In the medical domain, for instance, unveiling the mechanisms behind a disease often has higher priority than the diagnostic itself since it might dictate or guide potential treatments and research directions. One of the most popular approaches to explain model global predictions is the permutation importance where the performance on permuted data is benchmarked against the baseline. However, this method and other related approaches will undervalue the importance of a feature in the presence of covariates since these cover part of its provided information. To address this issue, we propose Covered Information Disentanglement CID, a framework that considers all feature information overlap to correct the values provided by permutation importance. We further show how to compute \CID efficiently when coupled with Markov random fields. We demonstrate its efficacy in adjusting permutation importance first on a controlled toy dataset and discuss its effect on real-world medical data.

poster session 4 @ blue 3, poster session 9 @ blue 3, poster session 4, poster session 9

The Shapley value is one of the most important normative division scheme in cooperative game theory, satisfying basic axioms. However, some allocation according to the Shapley value may seem unfair to humans. In this paper, we develop an automatic method that generates intuitive explanations for a Shapley-based payoff allocation, which utilizes the basic axioms. Given a coalitional game, our method decomposes it to sub-games, for which it is easy to generate verbal explanations, and shows that the given game is composed of the sub-games. Since the payoff allocation for each sub-game is perceived as fair, the Shapley-based payoff allocation for the given game should seem fair as well. We run an experiment with 210 human participants and show that when applying our method, humans perceive Shapley-based payoff allocation as significantly more fair than when using a general standard explanation.

poster session 2 @ red 2, poster session 9 @ red 2, poster session 2, poster session 9

In practical machine learning, models are frequently updated, or corrected, to adapt to new datasets. In this study, we pose two challenges to model correction. First, the effects of corrections to the end-users need to be described explicitly, similar to standard software where the corrections are described as release notes. Second, the amount of corrections need to be small so that the corrected models perform similarly to the old models. In this study, we propose the first model correction method for classification models that resolves these two challenges. Our idea is to use an additional decision tree to correct the output of the old models. Thanks to the explainability of decision trees, the corrections are describable to the end-users, which resolves the first challenge. We resolve the second challenge by incorporating the amount of corrections when training the additional decision tree so that the effects of corrections to be small. Experiments on real data confirm the effectiveness of the proposed method compared to existing correction methods.

poster session 2 @ blue 1, poster session 9 @ blue 1, poster session 2, poster session 9

How do we perform efficient inference while retaining high translation quality? Existing neural machine translation models, such as Transformer, achieve high performance, but they decode words one by one, which is inefficient. Recent non-autoregressive translation models speed up the inference, but their quality is still inferior. In this work, we propose DSLP, a highly efficient and high-performance model for machine translation. The key insight is to train a non-autoregressive Transformer with Deep Supervision and feed additional Layer-wise Predictions. We conducted extensive experiments on four translation tasks (both directions of WMT'14 EN-DE and WMT'16 EN-RO). Results show that our approach consistently improves the BLEU scores compared with respective base models. Specifically, our best variant outperforms the autoregressive model on three translation tasks, while being 14.8 times more efficient in inference.

poster session 6 @ red 5, poster session 9 @ red 5, oral session 6 @ red 5, poster session 6, poster session 9, oral session 6

Natural Language Inference (NLI) models are known to learn from biases and artefacts within their training data, impacting how well they generalise to other unseen datasets. Existing de-biasing approaches focus on preventing the models from learning these biases, which can result in restrictive models and lower performance. We instead investigate teaching the model how a human would approach the NLI task, in order to learn features that will generalise better to previously unseen examples. Using natural language explanations, we supervise the model’s attention weights to encourage more attention to be paid to the words present in the explanations, significantly improving model performance. Our experiments show that the in-distribution improvements of this method are also accompanied by out-of-distribution improvements, with the supervised models learning from features that generalise better to other NLI datasets. Analysis of the model indicates that human explanations encourage increased attention on the important words, with more attention paid to words in the premise and less attention paid to punctuation and stopwords.

poster session 6 @ red 5, poster session 9 @ red 5, poster session 6, poster session 9

Recent work has shown the potential benefit of selective prediction systems that can learn to defer to a human when the predictions of the AI are unreliable, particularly to improve the reliability of AI systems in high-stakes applications like healthcare or conservation. However, most prior work assumes that human behavior remains unchanged when they solve a prediction task as part of a human-AI team as opposed to by themselves. We show that this is not the case by performing experiments to quantify human-AI interaction in the context of selective prediction. In particular, we study the impact of communicating different types of information to humans about the AI system's decision to defer. Using real-world conservation data and a selective prediction system that improves expected accuracy over that of the human or AI system working individually, we show that this messaging has a significant impact on the accuracy of human judgements. Our results study two components of the messaging strategy: 1) Whether humans are informed about the prediction of the AI system and 2) Whether they are informed about the decision of the selective prediction system to defer. By manipulating these messaging components, we show that it is possible to significantly boost human performance by informing the human of the decision to defer, but not revealing the prediction of the AI. We therefore show that it is vital to consider how the decision to defer is communicated to a human when designing selective prediction systems, and that the composite accuracy of a human-AI team must be carefully evaluated using a human-in-the-loop framework.

poster session 2 @ red 2, poster session 9 @ red 2, poster session 2, poster session 9

Out-of-distribution (O.O.D.) generalization remains to be a key challenge for real-world machine learning systems. We describe a method for O.O.D. generalization that, through training, encourages models to only preserve features in the network that are well reused across multiple training domains. Our method combines two complementary neuron-level regularizers with a probabilistic differentiable binary mask over the network, to extract a modular sub-network that achieves better O.O.D. performance than the original network. Preliminary evaluation on two benchmark datasets corroborates the promise of our method.

poster session 2 @ blue 2, poster session 9 @ blue 2, poster session 2, poster session 9

Conditional neural process (CNP) has been extensively applied into data analyzing tasks due to its excellent ability to make accurate predictions for incomplete data points. However, in literature there are only few works that studied the CNPin recommendation systems. In this work, we propose CCFP, which is a collaborative filtering method that differs from other CF models by incorporating CNP into encoder-decoder architecture. By analyzing the complete user-item interaction data, our model fits a global representation that can better rep-resenting the features of users and items. CCFP can significantly improve the recommendation performance compared to baselines by predicting items for the target users with their incomplete observation data.

poster session 5 @ blue 5, poster session 9 @ blue 5, poster session 5, poster session 9

This paper studies learning node representations with graph neural networks (GNNs) for unsupervised scenario. Specifically, we derive a theoretical analysis and provide an empirical demonstration about the non-steady performance of GNNs over different graph datasets, when the supervision signals are not appropriately defined. The performance of GNNs depends on both the node feature smoothness and the locality of graph structure. To smooth the discrepancy of node proximity measured by graph topology and node feature, we proposed SAIL - a novel self-augmented graph contrastive learning framework, with two complementary self-distilling regularization modules, i.e., intra- and inter-graph knowledge distillation. We demonstrate the competitive performance of SAIL on a variety of graph applications. Even with a single GNN layer, SAIL has consistently competitive or even better performance on various benchmark datasets, comparing with state-of-the-art baselines.

poster session 5 @ blue 5, poster session 9 @ blue 5, poster session 5, poster session 9

Understanding the multiple socially-acceptable future behaviors is an essential task for many vision applications. In this paper, we propose a tree-based method, termed as Social Interpretable Tree (SIT), to address this multi-modal prediction task, where a hand-crafted tree is built depending on the prior information of observed trajectory to model multiple future trajectories. Specifically, a path in the tree from the root to leaf represents an individual possible future trajectory. SIT employs a coarse-to-fine optimization strategy, in which the tree is first built by high-order velocity to balance the complexity and coverage of the tree and then optimized greedily to encourage multimodality. Finally, a teacher-forcing refining operation is used to predict the final fine trajectory. Compared with prior methods which leverage implicit latent variables to represent possible future trajectories, the path in the tree can explicitly explain the rough moving behaviors (e.g., go straight and then turn right), and thus provides better interpretability. Despite the hand-crafted tree, the experimental results on ETH-UCY and Stanford Drone datasets demonstrate that our method is capable of matching or exceeding the performance of state-of-the-art methods. Interestingly, the experiments show that the raw built tree without training outperforms many prior deep neural network based approaches. Meanwhile, our method presents sufficient flexibility in long-term prediction and different best-of-K predictions.

poster session 5 @ red 1, poster session 9 @ red 1, poster session 5, poster session 9

In Ontology-Based Data Management (OBDM), an abstraction of a source query q is a query over the ontology capturing the semantics of q in terms of the concepts and the relations available in the ontology. Since a perfect characterisation of a source query may not exist, the notions of best sound and complete approximations of an abstraction have been introduced and studied in the typical OBDM context, i.e., in the case where the ontology is expressed in DL-Lite, and source queries are expressed as unions of conjunctive queries (UCQs). Interestingly, if we restrict our attention to abstractions expressed as UCQs, even best approximations of abstractions are not guaranteed to exist. Thus, a natural question to ask is whether such limitations affect even larger classes of queries. In this paper, we answer this fundamental question for an essential class of queries, namely the class of monotone queries. We define a monotone query language based on disjunctive Datalog enriched with an epistemic operator, and show that its expressive power suffices for expressing the best approximations of monotone abstractions of UCQs.

poster session 2 @ red 4, poster session 9 @ red 4, poster session 2, poster session 9

Pre-training has become a standard paradigm in many computer vision tasks. However, most of the methods are generally designed on the RGB image domain. Due to the discrepancy between the two-dimensional image plane and the three-dimensional space, such pre-trained models fail to perceive spatial information and serve as sub-optimal solutions for 3D-related tasks. To bridge this gap, we aim to learn a spatial-aware visual representation that can describe the three-dimensional space and is more suitable and effective for these tasks. To leverage point clouds, which are much more superior in providing spatial information compared to images, we propose a simple yet effective 2D Image and 3D Point cloud Unsupervised pre-training strategy, called SimIPU. Specifically, we develop a multi-modal contrastive learning framework that consists of an intra-modal spatial perception module to learn a spatial-aware representation from point clouds and an inter-modal feature interaction module to transfer the capability of perceiving spatial information from the point cloud encoder to the image encoder, respectively. Positive pairs for contrastive losses are established by the matching algorithm and the projection matrix. The whole framework is trained in an unsupervised end-to-end fashion. To the best of our knowledge, this is the first study to explore contrastive learning pre-training strategies for outdoor multi-modal datasets, containing paired camera images and LIDAR point clouds.

poster session 2 @ red 3, poster session 9 @ red 3, poster session 2, poster session 9

Existential rule languages are a family of ontology languages that have been widely used in ontology-mediated query answering (OMQA). However, for most of them, the expressive power of representing domain knowledge for OMQA, known as the program expressive power, is not well-understood yet. In this paper, we establish a number of novel characterizations for the program expressive power of several important existential rule languages, including tuple-generating dependencies (TGDs), linear TGDs, as well as disjunctive TGDs. The characterizations employ natural model-theoretic properties, and automata-theoretic properties sometimes, which thus provide powerful tools for identifying the definability of domain knowledge for OMQA in these languages.

poster session 2 @ red 4, poster session 9 @ red 4, oral session 2 @ red 4, poster session 2, poster session 9, oral session 2

The cost of developing new drugs is estimated at billions of dollars per year. Identification of new molecules for drugs involves scanning existing bio-medical literature for relevant information. As the potential drug molecule is novel, retrieval of relevant information using a simple direct search is less likely to be productive. Identifying relevant papers is therefore a more complex and challenging task, which requires searching for information on molecules with similar characteristics to the novel drug. In this paper, we present the novel task of ranking documents based on novel molecule queries. Given a chemical molecular structure, we wish to rank medical papers that will contribute to a researcher's understanding of the novel molecule drug potential. We present a set of ranking algorithms and molecular embeddings to address the task. An extensive evaluation of the algorithms is performed over the molecular embeddings, studying their performance on a benchmark retrieval corpus, which we share with the community. Additionally, we introduce a heterogeneous edge-labeled graph embedding approach to address the molecule ranking task. Our evaluation shows that the proposed embedding model can significantly improve molecule ranking methods. The system is currently deployed in a targeted drug delivery and personalized medicine research laboratory.

poster session 4 @ red 6, poster session 9 @ red 6, poster session 4, poster session 9

Recent advances in efficient planning in deterministic or stochastic high-dimensional domains with continuous action spaces leverage backpropagation through a model of the environment to directly optimize action sequences. However, existing methods typically do not take risk into account when optimizing in stochastic domains, which can be incorporated efficiently in MDPs by optimizing a nonlinear utility function of the return distribution. We bridge this gap by introducing Risk-Aware Planning using PyTorch (RAPTOR), a novel unified framework for risk-sensitive planning through end-to-end optimization of commonly-studied risk-sensitive utility functions such as entropic utility, mean-variance optimization and CVaR. A key technical difficulty of our approach is that direct optimization of general risk-sensitive utility functions by backpropagation is impossible due to the presence of environment stochasticity. The novelty of RAPTOR lies in leveraging reparameterization of the state distribution, leading to a unique distributional perspective of end-to-end planning where the return distribution is utilized for sampling as well as optimizing risk-aware objectives by backpropagation in a unified framework. We evaluate and compare RAPTOR on three highly stochastic MDPs, including nonlinear navigation, HVAC control, and linear reservoir control, demonstrating the ability of RAPTOR to manage risk in complex continuous domains according to different notions of risk-sensitive utility.

poster session 2 @ blue 1, poster session 9 @ blue 1, poster session 2, poster session 9

The domain gap severely limits the transferability and scalability of object detectors trained in a specific domain when applied to a novel one. Most existing works bridge the domain gap through minimizing the domain discrepancy in the category space and aligning category-agnostic global features. Though great success, these methods model domain discrepancy with prototypes within a batch, yielding a biased estimation of domain-level distribution. Besides, the category-agnostic alignment leads to the disagreement of class-specific distributions in the two domains, further causing inevitable classification errors. To overcome these two challenges, we propose a novel Semantic Conditioned AdaptatioN (SCAN) framework such that well-modeled unbiased semantics can support semantic conditioned adaptation for precise domain adaptive object detection. Specifically, class-specific semantics crossing different images in the source domain are graphically aggregated as the input to learn an unbiased semantic paradigm incrementally. The paradigm is then sent to a lightweight manifestation module to obtain conditional kernels to serve as the role of extracting semantics from the target domain for better adaptation. Subsequently, conditional kernels are integrated into global alignment to support the class-specific adaptation in a designed Conditional Kernel guided Alignment (CKA) module. Meanwhile, rich knowledge of the unbiased paradigm is transferred to the target domain with a novel Graph-based Semantic Transfer (GST) mechanism, yielding the adaptation in the category-based feature space. Comprehensive experiments conducted on three adaptation benchmarks demonstrate that SCAN outperforms existing works by a large margin.

poster session 2 @ red 3, poster session 9 @ red 3, oral session 9 @ red 3, poster session 2, poster session 9, oral session 9

Optimization is often cast as a deterministic problem, where the solution is found through some iterative procedure such as gradient descent. However, when training neural networks the loss function changes over (iteration) time due to the randomized selection of a subset of the samples. This randomization turns the optimization problem into a stochastic one. We propose to consider the loss as a noisy observation with respect to some reference optimum. This interpretation of the loss allows us to adopt Kalman filtering as an optimizer, as its recursive formulation is designed to estimate unknown parameters from noisy measurements. Moreover, we show that the Kalman Filter dynamical model for the evolution of the unknown parameters can be used to capture the gradient dynamics of advanced methods such as Momentum and Adam. We call this stochastic optimization method KOALA, which is short for Kalman Optimization Algorithm with Loss Adaptivity. KOALA is an easy to implement, scalable, and efficient method to train neural networks. We provide convergence analysis and show experimentally that it yields parameter estimates that are on par with or better than existing state of the art optimization algorithms across several neural network architectures and machine learning tasks, such as computer vision and language modeling.

poster session 4 @ blue 3, poster session 9 @ blue 3, poster session 4, poster session 9

Due to the scarcity of annotated samples, the diversity between support set and query set becomes the main obstacle for few shot semantic segmentation. Most existing prototype-based approaches only exploit the prototype from the support feature and ignore the information from the query sample, failing to remove this obstacle.In this paper, we proposes a dual prototype network (DPNet) to dispose of few shot semantic segmentation from a new perspective. Along with the prototype extracted from the support set, we propose to build the pseudo-prototype based on foreground features in the query image. To achieve this goal, the cycle comparison module is developed to select reliable foreground features and generate the pseudo-prototype with them. Then, a prototype interaction module is utilized to integrate the information of the prototype and the pseudo-prototype based on their underlying correlation. Finally, a multi-scale fusion module is introduced to capture contextual information during the dense comparison between prototype (pseudo-prototype) and query feature. Extensive experiments conducted on two benchmarks demonstrate that our method exceeds previous state-of-the-arts with a sizable margin, verifying the effectiveness of the proposed method.

poster session 2 @ red 2, poster session 9 @ red 2, poster session 2, poster session 9

We consider the problem of acquiring causal representations and concepts in a reinforcement learning setting. Our approach defines a causal variable as being both manipulable by a policy, and able to predict the outcome. We thereby obtain a parsimonious causal graph in which interventions occur at the level of policies. The approach avoids defining a generative model of the data, prior pre-processing, or learning the transition kernel of the Markov decision process. Instead, causal variables and policies are determined by maximizing a new optimization target inspired by mediation analysis, which differs from the expected return. The maximization is accomplished using a generalization of Bellman's equation which is shown to converge, and the method finds meaningful causal representations in a simulated environment.

poster session 4 @ blue 3, poster session 9 @ blue 3, poster session 4, poster session 9

Explainable artificial intelligence has rapidly emerged since lawmakers have started requiring interpretable models for safety-critical domains. Concept-based neural networks have arisen as explainable-by-design methods as they leverage human-understandable symbols (i.e. concepts) to predict class memberships. However, most of these approaches focus on the identification of the most relevant concepts but do not provide concise, formal explanations of how such concepts are leveraged by the classifier to make predictions. In this paper, we propose a novel end-to-end differentiable approach enabling the extraction of logic explanations from neural networks using the formalism of First-Order Logic. The method relies on an entropy-based criterion which automatically identifies the most relevant concepts. We consider four different case studies to demonstrate that: (i) this entropy-based criterion enables the distillation of concise logic explanations in safety-critical domains from clinical data to computer vision; (ii) the proposed approach outperforms state-of-the-art white-box models in terms of classification accuracy.

poster session 4 @ blue 3, poster session 9 @ blue 3, poster session 4, poster session 9

Ordered Multi-valued Decision Diagram (MDD) is a compact representation used to model various constraints, such as regular constraints and table constraints. It can be particularly useful for representing ad-hoc problem specific constraints. Many algorithms have been proposed to enforce Generalized Arc Consistency (GAC) on MDD constraints. In this paper, we introduce a new compact representation called Binary Constraint Tree (BCT). We propose tree binary encodings to transform any MDD constraint into a BCT constraint. We also present a specialized algorithm enforcing GAC on the BCT constraint resulting from a MDD constraint. Experimental results on a large set of benchmarks show that the BCT GAC algorithm can significantly outperform state-of-the-art MDD as well as table GAC algorithms.

poster session 2 @ blue 4, poster session 9 @ blue 4, poster session 2, poster session 9

In this paper, we propose a new joint object detection and tracking (JoDT) framework for 3D object detection and tracking based on camera and LiDAR sensors. The proposed method, referred to as 3D DetecTrack, enables the detector and tracker to cooperate to generate a spatio-temporal representation of the camera and LiDAR data, with which 3D object detection and tracking are then performed. The detector constructs the spatio-temporal features via the weighted temporal aggregation of the spatial features obtained by the camera and LiDAR fusion. Then, the detector reconfigures the initial detection results using information from the tracklets maintained up to the previous time step. Based on the spatio-temporal features generated by the detector, the tracker associates the detected objects with previously tracked objects using a graph neural network (GNN). We devise a fully-connected GNN facilitated by a combination of rule-based edge pruning and attention-based edge gating, which exploits both spatial and temporal object contexts to improve tracking performance. The experiments conducted on both KITTI and nuScenes benchmarks demonstrate that the proposed 3D DetecTrack achieves significant improvements in both detection and tracking performances over baseline methods and achieves state-of-the-art performance among existing methods through collaboration between the detector and tracker.

poster session 5 @ red 1, poster session 9 @ red 1, poster session 5, poster session 9

Several methods for discovering interpretable directions in the latent space of pre-trained GANs have been proposed. Latent semantics discovered by unsupervised methods are less disentangled than supervised methods since they do not use pre-trained attribute classifiers. We propose Scale Ranking Estimator (SRE), which is trained using self-supervision. SRE enhances the disentanglement in directions obtained by existing unsupervised disentanglement techniques. These directions are updated to preserve the ordering of variation within each direction in latent space. Qualitative and quantitative evaluation of the discovered directions demonstrates that our proposed method significantly improves disentanglement in various datasets. We also show that the learned SRE can be used to perform Attribute-based image retrieval task without any training.

poster session 2 @ red 2, poster session 9 @ red 2, poster session 2, poster session 9

The goal of stance detection is to determine the viewpoint expressed in a piece of text towards a target. These viewpoints or contexts are often expressed in many different languages depending on the user and the platform, which can be a local news outlet, a social media platform, a news forum, etc. Most research in stance detection, however, has been limited to working with a single language and on a few limited targets, with little work on cross-lingual stance detection. Moreover, non-English sources of labelled data are often scarce and present additional challenges. Recently, large multilingual language models have substantially improved the performance on many non-English tasks, especially such with limited numbers of examples. This highlights the importance of model pre-training and its ability to learn from few examples. In this paper, we present the most comprehensive study of cross-lingual stance detection to date: we experiment with 15 diverse datasets in 12 languages from 6 language families, and with 6 low-resource evaluation settings each. For our experiments, we build on pattern-exploiting training, proposing the addition of a novel label encoder to simplify the verbalisation procedure. We further propose sentiment-based generation of stance data for pre-training, which shows sizeable improvement of more than 6% F1 absolute in low-shot settings compared to several strong baselines.

poster session 6 @ red 5, poster session 9 @ red 5, oral session 9 @ red 5, poster session 6, poster session 9, oral session 9

Detecting rumors on social media has become particular important due to the rapid dissemination and adverse impacts on our lives. Though a set of rumor detection models have exploited the message propagation structural or temporal information, they seldom model them altogether to enjoy the best of both worlds. Moreover, the dynamics of knowledge information associated with the comments are not involved, either. To this end, we propose a novel Dual-Dynamic Graph Convolutional Networks, termed as DDGCN, which can model the dynamics of messages in propagation as well as the dynamics of the background knowledge from Knowledge graphs in one unified framework. Specifically, two Graph Convolutional Networks are adopted to capture the above two types of structure information at different time stages, which are then combined with a temporal fusing unit. This allows for learning the dynamic event representations in a more fine-grained manner, and incrementally aggregating them to capture the cascading effect for better rumor detection. Extensive experiments on two public real-world datasets demonstrate that our proposal yields significant improvements compared to strong baselines and can detect rumors at early stages.

poster session 5 @ blue 5, poster session 9 @ blue 5, poster session 5, poster session 9

The success of deep neural nets heavily relies on their ability to encode complex relations between their input and their output. While this property serves to fit the training data well, it also obscures the mechanism that drives prediction. This study aims to reveal hidden concepts by employing an intervention mechanism that shifts the predicted class based on discrete variational autoencoders. An explanatory model then visualizes the encoded information from any hidden layer and its corresponding intervened representation. By the assessment of differences between the original representation and the intervened representation, one can determine the concepts that can alter the class, hence providing interpretability. We demonstrate the effectiveness of our approach on CelebA, where we show various visualizations for bias in the data and suggest different interventions to reveal and change bias.

poster session 4 @ blue 3, poster session 9 @ blue 3, poster session 4, poster session 9

Semi-supervised video object segmentation (VOS) refers to segmenting the target object in remaining frames given its annotation in the first frame, which has been actively studied in recent years. The key challenge lies in finding effective ways to exploit the spatio-temporal context of past frames to help learn discriminative target representation of current frame. In this paper, we propose a novel Siamese network with a specifically designed interactive transformer, called SITVOS, to enable effective context propagation from historical to current frames. Technically, we use the transformer encoder and decoder to handle the past frames and current frame separately, i.e., the encoder encodes robust spatio-temporal context of target object from the past frames, while the decoder takes the feature embedding of current frame as the query to retrieve the target from the encoder output. To further enhance the target representation, a feature interaction module (FIM) is devised to promote the information flow between the encoder and decoder. Moreover, we employ the Siamese architecture to extract backbone features of both past and current frames, which enables feature reuse and is more efficient than existing methods. Experimental results on three challenging benchmarks validate the superiority of SITVOS over state-of-the-art methods. Code is available at https://github.com/LANMNG/SITVOS.

poster session 5 @ red 1, poster session 9 @ red 1, poster session 5, poster session 9

Graph neural networks (GNNs) have achieved tremendous success in many graph learning tasks such as node classification, graph classification and link prediction. For the classification task, GNNs' performance often highly depends on the number of labeled nodes and thus could be significantly hampered due to the expensive annotation cost. The sparse literature on active learning for GNNs has primarily focused on selecting only one sample each iteration, which becomes inefficient for large scale datasets. In this paper, we study the batch active learning setting for GNNs where the learning agent can acquire labels of multiple samples at each time. We formulate batch active learning as a cooperative multi-agent reinforcement learning problem and present a novel reinforced batch-mode active learning framework (\bigene). To avoid the combinatorial explosion of the joint action space, we introduce a value decomposition method that factorizes the total $Q$-value into the average of individual $Q$-values. Moreover, we propose a novel multi-agent Q-network consisting of a graph convolutional network (GCN) component and a gated recurrent unit (GRU) component. The GCN component takes both the informativeness and inter-dependences between nodes into account and the GRU component enables the agent to consider interactions between selected nodes in the same batch. Experimental results on multiple public datasets demonstrate the effectiveness and efficiency of our proposed method.

poster session 2 @ blue 2, poster session 9 @ blue 2, oral session 9 @ blue 2, poster session 2, poster session 9, oral session 9

The deployment of vaccines across the US provides significant defense against serious illness and death from COVID-19. Over 70% of vaccine-eligible Americans are at least partially vaccinated, but there are pockets of the population that are under-vaccinated, such as in rural areas and some demographic groups (e.g. age, race, ethnicity). These pockets are extremely susceptible to the Delta variant, exacerbating the healthcare crisis and increasing the risk of new variants. In this paper, we describe a data-driven model that provides real-time support to Virginia public health officials by recommending mobile vaccination site placement in order to target under-vaccinated populations. Our strategy uses fine-grained mobility data, along with US Census and vaccination uptake data, to identify locations that are most likely to be visited by unvaccinated individuals. We further extend our model to choose locations that maximize vaccine uptake among hesitant groups. We show that the top recommended sites vary substantially across some demographics, demonstrating the value of developing customized recommendation models that integrate fine-grained, heterogeneous data sources. We also validate our recommendations by analyzing the success rates of deployed vaccine sites, and show that sites placed closer to our recommended areas administered higher numbers of doses. Our model is the first of its kind to consider evolving mobility patterns in real-time for suggesting placement strategies customized for different targeted demographic groups.

poster session 4 @ red 6, poster session 9 @ red 6, poster session 4, poster session 9

Multi-label image recognition is a fundamental yet practical task because real-world images inherently possess multiple semantic labels. However, it is difficult to collect large-scale multi-label annotations due to the complexity of both the input images and output label spaces. To reduce the annotation cost, we propose a structured semantic transfer (SST) framework that enables training multi-label recognition models with partial labels, i.e., merely some labels are known while other labels are missing (also called unknown labels) per image. The framework consists of two complementary transfer modules that explore within-image and cross-image semantic correlations to transfer knowledge of known labels to generate pseudo labels for unknown labels. Specifically, an intra-image semantic transfer module learns image-specific label co-occurrence matrix and maps the known labels to complement unknown labels based on this matrix. Meanwhile, a cross-image transfer module learns category-specific feature similarities and helps complement unknown labels with high similarities. Finally, both known and generated labels are used to train the multi-label recognition models. Extensive experiments on the Microsoft COCO, Visual Genome and Pascal VOC datasets show that the proposed SST framework obtains superior performance over current state-of-the-art algorithms.

poster session 2 @ red 3, poster session 9 @ red 3, poster session 2, poster session 9

It is a consensus that small models perform quite poorly under the paradigm of self-supervised contrastive learning. Existing methods usually adopt a large off-the-shelf model to transfer knowledge to the small one via distillation. Despite their effectiveness, distillation-based methods may not be suitable for some resource-restricted scenarios due to the huge computational expenses of deploying a large model. In this paper, we study the issue of training self-supervised small models without distillation signals. We first evaluate the representation spaces of the small models and make two non-negligible observations: (i) the small models can complete the pretext task without overfitting despite their limited capacity and (ii) they universally suffer the problem of over clustering. Then we verify multiple assumptions that are considered to alleviate the over-clustering phenomenon. Finally, we combine the validated techniques and improve the baseline performances of five small architectures with considerable margins, which indicates that training small self-supervised contrastive models is feasible even without distillation signals. The code is available at \textit{https://github.com/WOWNICE/ssl-small}.

poster session 2 @ red 3, poster session 9 @ red 3, oral session 2 @ red 3, poster session 2, poster session 9, oral session 2

This paper addresses temporal sentence grounding. Previous works typically solve this task by learning frame-level video features and align them with the textual information. A major limitation of these works is that they fail to distinguish ambiguous video frames with subtle appearance differences due to frame-level feature extraction. Recently, a few methods adopt Faster R-CNN to extract detailed object features in each frame to differentiate the fine-grained appearance similarities. However, the object-level features extracted by Faster R-CNN suffer from missing motion analysis since the object detection model lacks temporal modeling. To solve this issue, we propose a novel Motion-Appearance Reasoning Network (MARN), which incorporates both motion-aware and appearance-aware object features for better reasoning the semantic relations between objects. Specifically, we first introduce two individual video encoders to embed the video into corresponding motion-oriented and appearance-aspect object representations. Then, we develop separate motion and appearance branches to learn motion-guided and appearance-guided object relations, respectively. At last, both motion and appearance information from two branches are associated to generate more representative features for final grounding. Extensive experiments on two challenging datasets (Charades-STA and TACoS) show that our proposed MARN significantly outperforms previous state-of-the-art methods.

poster session 2 @ red 4, poster session 9 @ red 4, poster session 2, poster session 9

The Moran process is a classic stochastic process that models invasion dynamics on graphs. A single ``mutant'' (e.g., a new opinion, strain, social trait etc.) invades a population of residents spread over the nodes of a graph. The mutant fitness advantage $\delta\geq 0$ determines how aggressively mutants propagate to their neighbors. The quantity of interest is the fixation probability, i.e., the probability that the initial mutant eventually takes over the whole population. However, in realistic settings, the invading mutant has an advantage only in certain locations. E.g., the ability to metabolize a certain sugar is an advantageous trait to bacteria only when the sugar is actually present in their surroundings. In this paper we introduce the positional Moran process, a natural generalization in which the mutant fitness advantage is only realized on specific nodes called active nodes, and study the problem of fixation maximization: given a budget $k$, choose a set of $k$ active nodes that maximize the fixation probability of the invading mutant. We show that the problem is NP-hard, while the optimization function is not submodular, thus indicating strong computational hardness. We focus on two natural limits. In the limit of $\delta\to\infty$ (strong selection), although the problem remains NP-hard, the optimization function becomes submodular and thus admits a constant-factor approximation using a simple greedy algorithm. In the limit of $\delta\to 0$ (weak selection), we show that we can obtain a tight approximation in $O(n^{2\cdot \omega})$ time, where $\omega$ is the matrix-multiplication exponent. An experimental evaluation of the new algorithms along with some proposed heuristics corroborates our results.

poster session 4 @ blue 6, poster session 9 @ blue 6, oral session 9 @ blue 6, poster session 4, poster session 9, oral session 9

For personalized ranking models, the well-calibrated probability of an item being preferred by a user has great practical value. While existing work shows promising results in image classification, probability calibration has not been much explored for personalized ranking. In this paper, we aim to estimate the calibrated probability of how likely a user will prefer an item. We investigate various parametric distributions and propose two parametric calibration methods, namely Gaussian calibration and Gamma calibration. Each proposed method can be seen as a post-processing function that maps the ranking scores of pre-trained models to well-calibrated preference probabilities, without affecting the recommendation performance. We also design the unbiased empirical risk minimization framework that guides the calibration methods to learning of true preference probability from the biased user-item interaction dataset. Extensive evaluations with various personalized ranking models on real-world datasets show that both the proposed calibration methods and the unbiased empirical risk minimization significantly improve the calibration performance.

poster session 5 @ blue 5, poster session 9 @ blue 5, oral session 5 @ blue 5, poster session 5, poster session 9, oral session 5

In this paper, we consider the problem of lacking theoretical foundation and low execution efficiency of the instance selection methods based on the $k$-nearest neighbour rule when processing large-scale data. We point out that the core idea of these methods can be explained from the perspective of Bayesian decision theory, that is, to find which instances are reducible, irreducible, and deleterious. Then, based on the percolation theory, we establish the relationship between these three types of instances and local homogeneous cluster (i.e., a set of instances with the same labels). Finally, we propose a method based on an accelerated $k$-means algorithm to construct local homogeneous clusters and remove the superfluous instances. The performance of our method is studied on extensive synthetic and benchmark data sets. Our proposed method can handle large-scale data more effectively than the state-of-the-art instance selection methods.

poster session 5 @ blue 5, poster session 9 @ blue 5, poster session 5, poster session 9

Multi-Agent Path Finding (MAPF) is the problem of finding a set of collision-free paths for a team of agents in a common environment. MAPF is NP-hard to solve optimally and, in some cases, also bounded suboptimally. It is thus time-consuming for (bounded-sub)optimal solvers to solve large MAPF instances. Anytime algorithms find solutions quickly for large instances and then improve them to close-to-optimal ones over time. In this paper, we improve the current state-of-the-art anytime solver MAPF-LNS, that first finds an initial solution fast and then repeatedly replans the paths of subsets of agents via Large Neighborhood Search (LNS). It generates the subsets of agents for replanning by randomized destroy heuristics, but not all of them increase the solution quality substantially. We propose to use machine learning to learn how to select a subset of agents from a collection of subsets, such that replanning increases the solution quality more. We show experimentally that our solver, MAPF-ML-LNS, significantly outperforms MAPF-LNS on the standard MAPF benchmark set in terms of both the speed of improving the solution and the final solution quality.

poster session 4 @ blue 6, poster session 9 @ blue 6, poster session 4, poster session 9

Most recent semantic segmentation methods adopt a U-Net framework with an encoder-decoder architecture. It is still challenging for U-Net with a simple skip connection scheme to model the global multi-scale context: 1) Not each skip connection setting is effective due to the issue of incompatible feature sets of encoder and decoder stage, even some skip connection negatively influence the segmentation performance; 2) The original U-Net is worse than the one without any skip connection on some datasets. Based on our findings, we propose a new segmentation framework, named UCTransNet (with a proposed CTrans module in U-Net), from the channel perspective with attention mechanism. Specifically, the CTrans (Channel Transformer) module is an alternate of the U-Net skip connections, which consists of a sub-module to conduct the multi-scale Channel Cross fusion with Transformer (named CCT) and a sub-module Channel-wise Cross-Attention (named CCA) to guide the fused multi-scale channel-wise information to effectively connect to the decoder features for eliminating the ambiguity. Hence, the proposed connection consisting of the CCT and CCA is able to replace the original skip connection to solve the semantic gaps for an accurate automatic medical image segmentation. The experimental results suggest that our UCTransNet produces more precise segmentation performance and achieves consistent improvements over the state-of-the-art for semantic segmentation across different datasets and conventional architectures involving transformer or U-shaped framework. Code: https://github.com/McGregorWwww/UCTransNet.

poster session 2 @ red 4, poster session 9 @ red 4, poster session 2, poster session 9

More than US$ 27 billion is estimated to have been paid-out in farm support in USA alone since 1991 in response to climate change impacts on agriculture, with costs likely continuing to rise. With the wider adoption of precision agriculture - an agriculture management strategy that involves gathering, processing and analyzing temporal, spatial and individual data - in both developed and developing countries, there is an increasing opportunity to harness accumulating, shareable, big data using artificial intelligence (AI) methods, collected from weather stations, field sensor networks, Internet-of-Things devices, unmanned aerial vehicles, and earth observational satellites. This requires smart algorithms tailored to agricultural data types, integrated into digital solutions that are viable, flexible, and scalable for wide deployment for a wide variety of agricultural users and decision-makers. We discuss a novel AI approach that addresses the real-world problem of developing a viable solution for reliably, timely, and cost-effectively forecasting crop status across large agricultural regions using Earth observational information in near-real-time. Our approach is based on extracting time-conditioned topological features which characterize complex spatio-temporal dependencies between crop production regions and integrating such topological signatures into Long Short Term Memory (LSTM). We discuss utility and limitations of the resulting zigzag persistence-based LSTM (ZZTop-LSTM) as a new tool for developing more informed crop insurance rate-making and accurate tracking of changing risk exposures and vulnerabilities within insurance risk areas.

poster session 1 @ red 6, poster session 9 @ red 6, poster session 1, poster session 9

MAX k-SAT is one of canonical NP-hard problems. Its variation called random MAX k-SAT problem was suggested in order to understand how hard it is to solve instances of the problem on average. The most common random model from which random instances get sampled is the uniform model. However, the uniform model, while useful for studying properties of the space of all k-CNF formulas as a whole, cannot capture all the structural properties we observe in the real-world instances. Therefore, we propose to use another random model called configuration model, which is able to produce instances with an arbitrary variable's degree distribution. Thus, we may focus and ``probe'' different regions of the space of all k-CNF formulas. There are many questions one may ask about the instances from configuration model, and in this paper we study how effective the pure literal elimination rule (or heuristic) performs when solving random MAX k-SAT instances having an arbitrary but fixed variable's degree distribution. We provide an equality that depends on the distribution of degrees, solving which one obtains the number of clauses the pure literal elimination rule satisfies. We also show how the distribution of variable degrees changes over time as the heuristic progresses.

poster session 2 @ blue 4, poster session 9 @ blue 4, oral session 9 @ blue 4, poster session 2, poster session 9, oral session 9

Bandit algorithms are widely used in sequential decision problems to maximize the cumulative reward. One potential application is mobile health, where the goal is to promote the user's health through personalized interventions based on user specific information acquired through wearable devices. Important considerations include the type of, and frequency with which data is collected (e.g. GPS, or continuous monitoring), as such factors can severely impact app performance and users’ adherence. In order to balance the need to collect data that is useful with the constraint of impacting app performance, one needs to be able to assess the usefulness of variables. Bandit feedback data are sequentially correlated, so traditional testing procedures developed for independent data cannot apply. Recently, a statistical testing procedure was developed for the actor-critic bandit algorithm (Lei et al., 2017). An actor-critic algorithm maintains two separate models, one for the actor, the action selection policy, and the other for the critic, the reward model. The performance of the algorithm as well as the validity of the test are guaranteed only when the critic model is correctly specified. However, misspecification is frequent in practice due to incorrect functional form or missing covariates. In this work, we propose a modified actor-critic algorithm which is robust to critic misspecification and derive a novel testing procedure for the actor parameters in this case.

poster session 2 @ blue 1, poster session 9 @ blue 1, poster session 2, poster session 9

The advancement in Image-to-Image translation techniques using generative Deep Learning-based approaches has shown promising results for the challenging task of inpainting-based 3D view synthesis. At the same time, even the current 3D view synthesis methods often create distorted structures or blurry textures inconsistent with surrounding areas. We analyzed the recently proposed algorithms for inpainting-based 3D view synthesis and observed that these algorithms no longer produce stretching and black holes. However, the existing databases such as IETR, IRCCyN, and IVY have 3D-generated views with these artifacts. This observation suggests that the existing 3D view synthesis quality assessment algorithms can not judge the quality of most recent 3D synthesized views. With this view, through this abstract, we analyze the need for a new large-scale database and a new perceptual quality metric oriented for 3D views using a test dataset.

poster session 5 @ red 1, poster session 9 @ red 1, poster session 5, poster session 9

Architectures that model language and vision together havereceived much attention in recent years. Nonetheless, most tasks in this field focus on end-to-end applications without providing insights on whether it is the underlying semantics of visual objects or words that is captured. In this paper we draw on the established Definition Modeling paradigm and enhance it by grounding, for the first time, textual definitions to visual representations. We name this new task Visual Definition Modeling and put forward DEMETER and DIONYSUS, two benchmarks where, given an image as context, models have to generate a textual definition for a target being either i) a word that describes the image, or ii) an object patch therein. To measure the difficulty of our tasks we finetuned six different baselines and analyzed their performances, which show that a text-only encoder-decoder model is more effective than models pretrained for handling inputs of both modalities concurrently. This demonstrates the complexity of our benchmarks and encourages more research on text generation conditioned on multimodal inputs. The datasets for both benchmarks are available at https://github.com/SapienzaNLP/visual-definition-modeling as well as the code to reproduce our models.

poster session 6 @ red 5, poster session 9 @ red 5, oral session 6 @ red 5, poster session 6, poster session 9, oral session 6

It is important to estimate the local average treatment effect (LATE) when compliance with a treatment assignment is incomplete. The previously proposed methods for LATE estimation required all relevant variables to be jointly observed in a single dataset; however, it is sometimes difficult or even impossible to collect such data in many real-world problems for technical or privacy reasons. We consider a novel problem setting in which LATE, as a function of covariates, is nonparametrically identified from the combination of separately observed datasets. For estimation, we show that the direct least squares method, which was originally developed for estimating the average treatment effect under complete compliance, is applicable to our setting. However, model selection and hyperparameter tuning for the direct least squares estimator can be unstable in practice since it is defined as a solution to the minimax problem. We then propose a weighted least squares estimator that enables simpler model selection by avoiding the minimax objective formulation. Unlike the inverse probability weighted (IPW) estimator, the proposed estimator directly uses the pre-estimated weight without inversion, avoiding the problems caused by the IPW methods. We demonstrate the effectiveness of our method through experiments using synthetic and real-world datasets.

poster session 2 @ red 2, poster session 9 @ red 2, poster session 2, poster session 9

This paper considers deep visual recognition on long-tailed data. To make our method general, we tackle two applied scenarios, i.e. , deep classification and deep metric learning. Under the long-tailed data distribution, the most classes (i.e., tail classes) only occupy relatively few samples and are prone to lack of within-class diversity. A radical solution is to augment the tail classes with higher diversity. To this end, we introduce a simple and reliable method named Memory-based Jitter (MBJ). We observe that during training, the deep model constantly changes its parameters after every iteration, yielding the phenomenon of weight jitters. Consequentially, given a same image as the input, two historical editions of the model generate two different features in the deeply-embedded space, resulting in feature jitters. Using a memory bank, we collect these (model or feature) jitters across multiple training iterations and get the so-called Memory-based Jitter. The accumulated jitters enhance the within-class diversity for the tail classes and consequentially improves long-tailed visual recognition. With slight modifications, MBJ is applicable for two fundamental visual recognition tasks, i.e., deep image classification and deep metric learning (on long-tailed data). Extensive experiments on five long-tailed classification benchmarks and two deep metric learning benchmarks demonstrate significant improvement. Moreover, the achieved performance are on par with the state of the art on both tasks.

poster session 2 @ red 3, poster session 9 @ red 3, poster session 2, poster session 9

Conditional Density Estimation (CDE) has wide-reaching applicability to various real-world problems, such as spatial density estimation and environmental modelling. CDE estimates the probability density of a random variable rather than a single value and can thus model uncertainty and inverse problems. This task is inherently more complex than regression, and many algorithms suffer from overfitting, particularly when modelled with few labelled data points. For applications where unlabelled data is abundant but labelled data is scarce, we propose Wasserstein Laplacian Regularisation, a semi-supervised learning framework that allows CDE algorithms to leverage these unlabelled data. The framework minimises an objective function which ensures that the learned model is smooth along the manifold of the underlying data, as measured by Wasserstein distance. When applying our framework to Mixture Density Networks, the resulting semi-supervised algorithm can achieve similar performance to a supervised model with up to three times as many labelled data points on baseline datasets. We additionally apply our technique to the problem of remote sensing for chlorophyll-a estimation in inland waters.

poster session 2 @ blue 2, poster session 9 @ blue 2, poster session 2, poster session 9

Strategy synthesis for multi-agent systems has proved to be a hard task, even when limited to two-player games with safety objectives. Generalized strategy synthesis, an extension of generalized planning which aims to produce a single solution for multiple (possibly infinitely many) planning instances, is a promising direction to deal with the state-space explosion problem. In this paper, we formalize the problem of generalized strategy synthesis in the situation calculus. The synthesis task involves second-order theorem proving generally. Thus we consider strategies aiming to maintain invariants; such strategies can be verified with first-order theorem proving. We propose a sound but incomplete approach to synthesize invariant strategies by adapting the framework of counterexample-guided refinement. The key idea for refinement is to generate a strategy using a model checker for a game constructed from the counterexample, and use it to refine the candidate general strategy. We implemented our method and did experiments with a number of game problems. Our system can successfully synthesize solutions for most of the domains within a reasonable amount of time.

poster session 2 @ red 4, poster session 9 @ red 4, oral session 2 @ red 4, poster session 2, poster session 9, oral session 2

Walrasian equilibrium is a prominent market equilibrium notion, but rarely exists in markets with indivisible items. We introduce a new market equilibrium notion, called two-price equilibrium (2PE). A 2PE is a relaxation of Walrasian equilibrium, where instead of a single price per item, every item has two prices: one for the item's owner and a (possibly) higher one for all other buyers. Thus, a 2PE is given by a tuple $(\textbf{S},\mathbf{\hat{p}},\mathbf{\check{p}})$ of an allocation $\allocs$ and two price vectors $\mathbf{\hat{p}},\mathbf{\check{p}}$, where every buyer $i$ is maximally happy with her bundle $S_i$, given prices $\mathbf{\check{p}}$ for items in $S_i$ and prices $\mathbf{\hat{p}}$ for all other items. 2PE generalizes previous market equilibrium notions, such as conditional equilibrium, and is related to relaxed equilibrium notions like endowment equilibrium. We define the {\em discrepancy} of a 2PE --- a measure of distance from Walrasian equilibrium --- as the sum of differences $\hat{p}_j-\check{p}_j$ over all items (normalized by social welfare). We show that the social welfare degrades gracefully with the discrepancy; namely, the social welfare of a 2PE with discrepancy $d$ is at least a fraction $\frac{1}{d+1}$ of the optimal welfare. We use this to establish welfare guarantees for markets with subadditive valuations over identical items. In particular, we show that every such market admits a 2PE with at least $1/7$ of the optimal welfare. This is in contrast to Walrasian equilibrium or conditional equilibrium which may not even exist. Our techniques provide new insights regarding valuation functions over identical items, which we also use to characterize instances that admit a WE.

poster session 4 @ blue 6, poster session 9 @ blue 6, poster session 4, poster session 9

Predictive maintenance systems have the potential to significantly reduce costs for maintaining aircraft fleets as well as provide improved safety by detecting maintenance issues before they come severe. However, the development of such systems has been limited due to a lack of publicly labeled multivariate time series (MTS) sensor data. MTS classification has advanced greatly over the past decade, but there is a lack of sufficiently challenging benchmarks for new methods. This work introduces the NGAFID Maintenance Classification (NGAFID-MC) dataset as a novel benchmark in terms of difficulty, number of samples, and sequence length. NGAFID-MC consists of over 7,500 labeled flights, representing over 11,500 hours of per second flight data recorder readings of 23 sensor parameters. Using this benchmark, we demonstrate that Recurrent Neural Network (RNN) methods are not well suited for capturing temporally distant relationships and propose a new architecture called Convolutional Multiheaded Self Attention (Conv-MHSA) that achieves greater classification performance at greater computational efficiency. We also demonstrate that image inspired augmentations of cutout, mixup, and cutmix, can be used to reduce overfitting and improve generalization in MTS classification. Our best trained models have been incorporated back into the NGAFID to allow users to potentially detect flights that require maintenance as well as provide feedback to further expand and refine the NGAFID-MC dataset.

poster session 9 @ red 6, poster session 7 @ red 6, poster session 9, poster session 7

We present a collaborative learning method called Mutual Contrastive Learning (MCL) for general visual representation learning. The core idea of MCL is to perform mutual interaction and transfer of contrastive distributions among a cohort of networks. A crucial component of MCL is Interactive Contrastive Learning (ICL). Compared with vanilla contrastive learning, ICL can aggregate cross-network embedding information and maximize the lower bound to the mutual information between two networks. This enables each network to learn extra contrastive knowledge from others, leading to better feature representations for visual recognition tasks. We emphasize that the resulting MCL is conceptually simple yet empirically powerful. It is a generic framework that can be applied to both supervised and self-supervised representation learning. Experimental results on image classification and transfer learning to object detection show that MCL can lead to consistent performance gains, demonstrating that MCL can guide the network to generate better feature representations. Code is available at https://github.com/winycg/MCL.

poster session 2 @ red 3, poster session 9 @ red 3, oral session 2 @ red 3, poster session 2, poster session 9, oral session 2

Invariance to diverse types of image corruption, such as noise, blurring, or colour shifts, is essential to establish robust models in computer vision. Data augmentation has been proven to improve robustness against common corruptions. However, existing augmentation strategies for boosting corruption robustness produce samples that deviate significantly from the underlying data manifold. As a result, performance is skewed toward certain types of corruption. To address this issue, we propose a multi-source vicinal transfer augmentation (VITA) method for generating diverse on-manifold samples. The proposed VITA consists of two complementary parts: tangent transfer and integration of multi-source vicinal samples. The tangent transfer creates initial augmented samples for improving corruption robustness. The integration employs a generative model to characterize the underlying manifold built by vicinal samples, facilitating in the generation of on-manifold samples. Our proposed VITA outperforms other state-of-the-art augmentation methods significantly, as demonstrated by extensive experiments on corruption benchmarks.

poster session 2 @ red 3, poster session 9 @ red 3, poster session 2, poster session 9

Planar object tracking plays an important role in AI applications, such as robotics, visual servoing, and visual SLAM. Although the previous planar trackers work well in most scenarios, it is still a challenging task due to the rapid motion and large transformation between two consecutive frames. The essential reason behind this problem is that the condition number of such a non-linear system changes unstably when the searching range of the homography parameter space becomes larger. To this end, we propose a novel Homography Decomposition Networks (HDN) approach that drastically reduces and stabilizes the condition number by decomposing the homography transformation into two groups. Specifically, a similarity transformation estimator is designed to predict the first group robustly by a deep convolution equivariant network. By taking advantage of the scale and rotation estimation with high confidence, a residual transformation is estimated by a simple regression model. Furthermore, the proposed end-to-end network is trained in a semi-supervised fashion. Extensive experiments show that our proposed approach outperforms the state-of-the-art planar tracking methods at a large margin on the challenging POT, UCSB and POIC datasets.

poster session 5 @ red 1, poster session 9 @ red 1, oral session 9 @ red 1, poster session 5, poster session 9, oral session 9

Graph Convolutional Network (GCN) has shown remarkable potential of exploring graph representation. However, the GCN aggregating mechanism fails to generalize to networks with heterophily where most nodes have neighbors from different classes, which commonly exists in real-world networks. In order to make the propagation and aggregation mechanism of GCN suitable for both homophily and heterophily (or even their mixture), we introduce block modelling into the framework of GCN so that it can realize “block-guided classified aggregation”, and automatically learn the corresponding aggregation rules for neighbors of different classes. By incorporating block modelling into the aggregation process, GCN is able to automatically aggregate information from homophilic and heterophilic neighbors discriminately according to their homophily degree. We compared our algorithm with state-of-art methods which deal with the heterophily problem. Empirical results demonstrate the superiority of our new approach over existing methods in heterophilic datasets while maintaining a competitive performance in homophilic datasets.

poster session 5 @ blue 5, poster session 9 @ blue 5, oral session 9 @ blue 5, poster session 5, poster session 9, oral session 9

In many visual systems, visual tracking often bases on RGB image sequences, in which some targets are invalid in low-light conditions, and tracking performance is thus affected significantly. Introducing other modalities such as depth and infrared data is an effective way to handle imaging limitations of individual sources, but multi-modal imaging platforms usually require elaborate designs and cannot be applied in many real-world applications at present. Near-infrared (NIR) imaging becomes an essential part of many surveillance cameras, whose imaging is switchable between RGB and NIR based on the light intensity. These two modalities are heterogeneous with very different visual properties and thus bring big challenges for visual tracking. However, existing works have not studied this challenging problem. In this work, we address the cross-modal object tracking problem and contribute a new video dataset, including 654 cross-modal image sequences with over 481K frames in total, and the average video length is more than 735 frames. To promote the research and development of cross-modal object tracking, we propose a new algorithm, which learns the modality-aware target representation to mitigate the appearance gap between RGB and NIR modalities in the tracking process. It is plug-and-play and could thus be flexibly embedded into different tracking frameworks. Extensive experiments on the dataset are conducted, and we demonstrate the effectiveness of the proposed algorithm in two representative tracking frameworks against 19 state-of-the-art tracking methods. Dataset, code, model and results are available at https://github.com/mmic-lcl/source-code.

poster session 5 @ red 1, poster session 9 @ red 1, poster session 5, poster session 9

Investigating the reasoning abilities of transformer models, and discovering new challenging tasks for them, has been a topic of much interest. Recent studies have found these models to be surprisingly strong at performing deductive reasoning over formal logical theories expressed in natural language. A shortcoming of these studies, however, is that they do not take into account that logical theories, when sampled uniformly at random, do not necessarily lead to hard instances. We propose a new methodology for creating challenging algorithmic reasoning datasets that focus on natural language satisfiability (NLSat) problems. The key idea is to draw insights from empirical sampling of hard propositional SATproblems and from complexity-theoretic studies of language. This methodology allows us to distinguish easy from hard instances, and to systematically increase the complexity of existing reasoning benchmarks such as RuleTaker. We find that current transformers, given sufficient training data, are surprisingly robust at solving the resulting NLSat problems of substantially increased difficulty. They also exhibit some degree of scale-invariance—the ability to generalize to problems of larger size and scope. Our results, however, reveal important limitations too: careful sampling of training data is crucial for building models that generalize to larger problems, and transformer models’ limited scale-invariance suggests they are far from learning robust deductive reasoning algorithms.

poster session 6 @ red 5, poster session 9 @ red 5, poster session 6, poster session 9

Deep learning has redefined AI thanks to the rise of artificial neural networks, which are inspired by neurological networks in the brain. Through the years, this dualism between AI and neuroscience has brought immense benefits to both fields, allowing neural networks to be used in a plethora of applications. Neural networks use an efficient implementation of reverse differentiation, called backpropagation (BP). This algorithm, however, is often criticized for its biological implausibility (e.g., lack of local update rules for the parameters). Therefore, biologically plausible learning methods that rely on predictive coding (PC), a framework for describing information processing in the brain, are increasingly studied. Recent works prove that these methods can approximate BP up to a certain margin on multilayer perceptrons (MLPs), and asymptotically on any other complex model, and that zero-divergence inference learning (Z-IL), a variant of PC, is able to exactly implement BP on MLPs. However, the recent literature shows also that there is no biologically plausible method yet that can exactly replicate the weight update of BP on complex models. To fill this gap, in this paper, we generalize (PC and) Z-IL by directly defining it on computational graphs, and show that it can perform exact reverse differentiation. What results is the first PC (and so biologically plausible) algorithm that is equivalent to BP in the way of updating parameters on any neural network, providing a bridge between the interdisciplinary research of neuroscience and deep learning. Furthermore, the above results in particular also immediately provide a novel local and parallel implementation of BP.

poster session 2 @ red 2, poster session 9 @ red 2, poster session 2, poster session 9

Stance detection is an important task, supporting many downstream tasks such as discourse parsing and modeling the propagation of fake news, rumors, and science denial. In this paper, we propose a novel framework for stance detection. Our framework is unsupervised and domain-independent. Given a claim and a multi-participant discussion, we construct the interaction network from which we derive topological embeddings for each speaker. These speaker embeddings enjoy the following property: speakers that share the same stance tend to be represented by similar vectors, while antipodal vectors represent speakers with opposing stances. These embeddings are then used to divide the speakers into stance-partitions. We evaluate our method on three different datasets from different platforms. Our method outperforms or is comparable with supervised models while providing confidence levels for its output. Furthermore, we demonstrate how the structural embeddings relate to the valence expressed by the speakers. Finally, we discuss some limitations inherent to the framework.

poster session 6 @ red 5, poster session 9 @ red 5, poster session 6, poster session 9

The recent advance in deep generative models outlines a promising perspective in the realm of Zero-Shot Learning (ZSL). Most generative ZSL methods use category semantic attributes plus a Gaussian noise to generate visual features. After generating unseen samples, this family of approaches effectively transforms the ZSL problem into a supervised classification scheme. However, the existing models use a single semantic attribute, which contains the complete attribute information of the category. The generated data also carry the complete attribute information, but in reality, visual samples usually have limited attributes. Therefore, the generated data from attribute could have incomplete semantics. Based on this fact, we propose a novel framework to boost ZSL by synthesizing diverse features. This method uses augmented semantic attributes to train the generative model, so as to simulate the real distribution of visual features. We evaluate the proposed model on four benchmark datasets, observing significant performance improvement against the state-of-the-art.

poster session 2 @ red 3, poster session 9 @ red 3, poster session 2, poster session 9

Knowledge graph completion (KGC) aims to infer missing information in incomplete knowledge graphs (KGs). Most previous works only consider the transductive scenario where entities are existing in KGs, which cannot work effectively for the inductive scenario containing emerging entities. Recently some graph neural network-based methods have been proposed for inductive KGC by aggregating neighborhood information to capture some uncertainty semantics from the neighboring auxiliary triples. But these methods ignore the more general relational semantics underlying all the known triples that can provide richer information to represent emerging entities so as to satisfy the inductive scenario. In this paper, we propose a novel model called CFAG, which utilizes two granularity levels of relational semantics in a coarse-grained aggregator (CG-AGG) and a fine-grained generative adversarial net (FG-GAN), for inductive KGC. The CG-AGG firstly generates entity representations with multiple semantics through a hypergraph neural network-based global aggregator and a graph neural network-based local aggregator, and the FG-GAN further enhances entity representations with specific semantics through conditional generative adversarial nets. Experimental results on benchmark datasets show that our model outperforms state-of-the-art models for inductive KGC.

poster session 5 @ blue 5, poster session 9 @ blue 5, oral session 5 @ blue 5, poster session 5, poster session 9, oral session 5

We present an approach to incorporating qualitative assertions of conditional irrelevance into belief revision, in order to address the limitations of existing work which considers only unconditional irrelevance. These assertions serve to enforce the requirement of minimal change to existing beliefs, while also suggesting a route to reducing the computational cost of belief revision by excluding irrelevant beliefs from consideration. In our approach, a knowledge engineer specifies a collection of multivalued dependencies that encode domain-dependent assertions of conditional irrelevance in the knowledge base. We consider these as capturing properties of the underlying domain which should be taken into account during belief revision. We introduce two related notions of what it means for a multivalued dependency to be taken into account by a belief revision operator: partial and full compliance. We provide characterisations of partially and fully compliant belief revision operators in terms of semantic conditions on their associated faithful rankings. Using these characterisations, we show that the constraints for partially and fully compliant belief revision operators are compatible with the AGM postulates. Finally, we compare our approach to existing work on unconditional irrelevance in belief revision.

poster session 2 @ red 4, poster session 9 @ red 4, poster session 2, poster session 9

Joint embedding (JE) is a way to encode multi-modal data into a vector space where text remains as the grounding key and other modalities like image are to be anchored with such keys. Meme is typically an image with embedded text onto it. Although, memes are commonly used for fun, they could also be used to spread hate and fake information. That along with its growing ubiquity over several social platforms has caused automatic analysis of memes to become a widespread topic of research. In this paper, we report our initial experiments on Memotion Analysis problem through joint embeddings. Results are marginally yielding SOTA.

poster session 5 @ red 1, poster session 9 @ red 1, poster session 5, poster session 9

The task of few-shot fine-grained recognition is to classify images belonging to subordinate categories merely depending on few examples. Due to the fine-grained nature, it is desirable to capture subtle but discriminative part-level patterns from limited training data, which makes it a challenging problem. In this paper, to generate fine-grained tailored representations for few-shot recognition, we propose a Dual Attention Network (\textsc{Dual Att-Net}) consisting of two dual branches of both hard- and soft-attentions. Specifically, by producing attention guidance from deep activations of input images, our hard-attention is realized by keeping a few useful deep descriptors and forming them as a bag of multi-instance learning. Since these deep descriptors could correspond to objects' parts, the advantage of modeling as a multi-instance bag is able to exploit inherent correlation of these fine-grained parts. On the other side, a soft attended activation representation can be obtained by applying attention guidance upon original activations, which brings comprehensive attention information as the counterpart of hard-attention. After that, both outputs of dual branches are aggregated as a holistic image embedding w.r.t. input images. By performing meta-learning, we can learn a powerful image embedding in such a metric space to generalize to novel classes. Experiments on three popular fine-grained benchmark datasets show that our \textsc{Dual Att-Net} obviously outperforms other existing state-of-the-art methods.

poster session 2 @ red 3, poster session 9 @ red 3, oral session 9 @ red 3, poster session 2, poster session 9, oral session 9

Online recommender systems should be always aligned with users' current interest to accurately suggest items that each user would like. Since user interest usually evolves over time, the update strategy should be flexible to quickly catch users' current interest from continuously generated new user-item interactions. Existing update strategies focus either on the importance of each user-item interaction or the learning rate for each recommender parameter, but such one-directional flexibility is insufficient to adapt to varying relationships between interactions and parameters. In this paper, we propose MeLON, a meta-learning based novel online recommender update strategy that supports two-directional flexibility. It is featured with an adaptive learning rate for each parameter-interaction pair for inducing a recommender to quickly learn users' up-to-date interest. The procedure of MeLON is optimized following a meta-learning approach: it learns how a recommender learns to generate the optimal learning rates for future updates. Specifically, MeLON first enriches the meaning of each interaction based on previous interactions and identifies the role of each parameter for the interaction; and then combines these two pieces of information to generate an adaptive learning rate. Theoretical analysis and extensive evaluation on three real-world online recommender datasets validate the effectiveness of MeLON.

poster session 5 @ blue 5, poster session 9 @ blue 5, poster session 5, poster session 9

In recent years, self-supervised representation learning for skeleton-based action recognition has been developed with the advance of contrastive learning methods. The existing contrastive learning methods use normal augmentations to construct similar positive samples, which limits the ability to explore novel movement patterns. In this paper, to make better use of the movement patterns introduced by extreme augmentations, a Contrastive Learning framework utilizing Abundant Information Mining for self-supervised action Representation (AimCLR) is proposed. First, the extreme augmentations and the Energy-based Attention-guided Drop Module (EADM) are proposed to obtain diverse positive samples, which bring novel movement patterns to improve the universality of the learned representations. Second, since directly using extreme augmentations may not be able to boost the performance due to the drastic changes in original identity, the Dual Distributional Divergence Minimization Loss (D3M Loss) is proposed to minimize the distribution divergence in a more gentle way. Third, the Nearest Neighbors Mining (NNM) is proposed to further expand positive samples to make the abundant information mining process more reasonable. Exhaustive experiments on NTU RGB+D 60, PKU-MMD, NTU RGB+D 120 datasets have verified that our AimCLR can significantly perform favorably against state-of-the-art methods under a variety of evaluation protocols with observed higher quality action representations. Our code is available at https://github.com/Levigty/AimCLR.

poster session 5 @ red 1, poster session 9 @ red 1, oral session 5 @ red 1, poster session 5, poster session 9, oral session 5

We approach the task of network congestion control in datacenters using Reinforcement Learning (RL). Successful congestion control algorithms can dramatically improve latency and overall network throughput. Until today, no such learning-based algorithms have shown practical potential in this domain. Evidently, the most popular recent deployments rely on rule-based heuristics that are tested on a predetermined set of benchmarks. Consequently, these heuristics do not generalize well to newly-seen scenarios. Contrarily, we devise an RL-based algorithm with the aim of generalizing to different configurations of real-world datacenter networks. We overcome challenges such as partial-observability, non-stationarity, and multi-objectiveness. We further propose a policy gradient algorithm that leverages the analytical structure of the reward function to approximate its derivative and improve stability. We show that these challenges prevent standard RL algorithms from operating within this domain. Our experiments, conducted on a realistic simulator that emulates communication networks' behavior, show that our method exhibits improved performance concurrently on the multiple considered metrics compared to the popular algorithms deployed today in real datacenters. Our algorithm is being productized to replace heuristics in some of the largest datacenters in the world.

poster session 9 @ red 6, poster session 7 @ red 6, poster session 9, poster session 7

Human emotions involve basic and compound facial expressions. However, current research on facial expression recognition (FER) mainly focuses on basic expressions, and thus fails to address the diversity of human emotions in practical scenarios. Meanwhile, existing work on compound FER relies heavily on abundant labeled compound expression training data, which are often laboriously collected under the professional instruction of psychology. In this paper, we study compound FER in the cross-domain few-shot learning setting, where only a few images of novel classes from the target domain are required as a reference. In particular, we aim to identify unseen compound expressions with the model trained on easily accessible basic expression datasets. To alleviate the problem of limited base classes in our FER task, we propose a novel Emotion Guided Similarity Network (EGS-Net), consisting of an emotion branch and a similarity branch, based on a two-stage learning framework. Specifically, in the first stage, the similarity branch is jointly trained with the emotion branch in a multi-task fashion. With the regularization of the emotion branch, we prevent the similarity branch from overfitting to sampled base classes that are highly overlapped across different episodes. In the second stage, the emotion branch and the similarity branch play a “two-student game” to alternately learn from each other, thereby further improving the inference ability of the similarity branch on unseen compound expressions. Experimental results on both in-the-lab and in-the-wild compound expression datasets demonstrate the superiority of our proposed method against several state-of-the-art methods.

poster session 2 @ red 2, poster session 9 @ red 2, poster session 2, poster session 9

This paper tackles the problem of semi-supervised learning when the set of labeled samples is limited to a small number of images per class, typically less than 10, problem that we refer to as barely-supervised learning. We analyze in depth the behavior of a state-of-the-art semi-supervised method, FixMatch, which relies on a weakly-augmented version of an image to obtain supervision signal for a more strongly-augmented version. We show that it frequently fails in barely-supervised scenarios, due to a lack of training signal when no pseudo-label can be predicted with high confidence. We propose a method to leverage self-supervised methods that provides training signal in the absence of confident pseudo-labels. We then propose two methods to refine the pseudo-label selection process which lead to further improvements.The first one relies on a per-sample history of the model predictions, akin to a voting scheme. The second iteratively up-dates class-dependent confidence thresholds to better explore classes that are under-represented in the pseudo-labels. Our experiments show that our approach performs significantly better on STL-10 in the barely-supervised regime,e.g. with 4 or 8 labeled images per class.

poster session 4 @ blue 6, poster session 9 @ blue 6, poster session 4, poster session 9

Reactive synthesis from high-level specifications that combine {\em hard} constraints expressed in Linear Temporal Logic ($\ltl$) with {\em soft} constraints expressed by discounted-sum (DS) rewards has applications in planning and reinforcement learning. An existing approach combines techniques from $\ltl$ synthesis with optimization for the DS rewards but has failed to yield a sound algorithm. An alternative approach combining $\ltl$ synthesis with satisficing DS rewards (rewards that achieve a threshold) is sound and complete for integer discount factors, but, in practice, a fractional discount factor is desired. This work extends the existing satisficing approach, presenting the first sound algorithm for synthesis from $\ltl$ and DS rewards with fractional discount factors. The utility of our algorithm is demonstrated on robotic planning domains.

poster session 2 @ blue 1, poster session 9 @ blue 1, oral session 2 @ blue 1, poster session 2, poster session 9, oral session 2

Hawkes processes are a special class of temporal point processes which exhibit a natural notion of causality, as occurrence of events in the past may increase the probability of events in the future. Discovery of the underlying influence network among the dimensions of multi-dimensional temporal processes is of high importance in disciplines where a high-frequency data is to model, e.g. in financial data or in seismological data. This paper approaches the problem of learning Granger-causal network in multi-dimensional Hawkes processes. We formulate this problem as a model selection task in which we follow the minimum description length (MDL) principle. Moreover, we propose a general algorithm for MDL-based inference using a Monte-Carlo method and we use it for our causal discovery problem. We compare our algorithm with the state-of-the-art baseline methods on synthetic and real-world financial data. The synthetic experiments demonstrate superiority of our method in causal graph discovery compared to the baseline methods with respect to the size of the data. The results of experiments with the G-7 bonds price data are consistent with the experts’ knowledge.

poster session 4 @ blue 3, poster session 9 @ blue 3, oral session 9 @ blue 3, poster session 4, poster session 9, oral session 9

Artificial intelligence (AI) is a promising technology to transform the healthcare industry. Due to the highly sensitive nature of patient data, federated learning (FL) is often leveraged to build models for smart healthcare applications. Existing deployed FL frameworks cannot address the key issues of varying data quality and heterogeneous data distributions across multiple institutions in this sector. In this paper, we report our experience developing and deploying the Contribution-Aware Federated Learning (CAFL) framework for smart healthcare. It provides an efficient and accurate approach to fairly evaluate FL participants' contribution to model performance without exposing their private data, and improves the FL model training protocol to allow the best performing intermediate models to be distributed to participants for FL training. Since its deployment in Yidu Cloud Technology Inc. in March 2021, CAFL has served 8 well-established medical institutions in China to build healthcare decision support models. It can perform contribution evaluations 2.84 times faster than the best existing approach, and has improved the average accuracy of the resulting models by 2.62% compared to the previous system (which is significant in industrial settings). To our knowledge, it is the first contribution-aware federated learning successfully deployed in the healthcare industry.

poster session 4 @ red 6, poster session 9 @ red 6, poster session 4, poster session 9

We address the poor scalability of learning algorithms for orthogonal recurrent neural networks via the use of stochastic coordinate descent on the orthogonal group, leading to a cost per iteration that increases linearly with the number of recurrent states. This contrasts with the cubic dependency of typical feasible algorithms such as stochastic Riemannian gradient descent, which prohibits the use of big network architectures. Coordinate descent rotates successively two columns of the recurrent matrix. When the coordinate (i.e., indices of rotated columns) is selected uniformly at random at each iteration, we prove convergence of the algorithm under standard assumptions on the loss function, stepsize and minibatch noise. In addition, we numerically show that the Riemannian gradient has an approximately sparse structure. Leveraging this observation, we propose a variant of our proposed algorithm that relies on the Gauss-Southwell coordinate selection rule. Experiments on a benchmark recurrent neural network training problem show that the proposed approach is a very promising step towards the training of orthogonal recurrent neural networks with big architectures.

poster session 4 @ blue 3, poster session 9 @ blue 3, poster session 4, poster session 9

Learning against label noise is a vital topic to guarantee a reliable performance for deep neural networks.Recent research usually refers to dynamic noise modeling with model output probabilities and loss values, and then separates clean and noisy samples.These methods have gained notable success. However, unlike cherry-picked data, existing approaches often cannot perform well when facing imbalanced datasets, a common scenario in the real world.We thoroughly investigate this phenomenon and point out two major issues that hinder the performance, i.e., inter-class loss distribution discrepancy and misleading predictions due to uncertainty.The first issue is that existing methods often perform class-agnostic noise modeling. However, loss distributions show a significant discrepancy among classes under class imbalance, and class-agnostic noise modeling can easily get confused with noisy samples and samples in minority classes.The second issue refers to that models may output misleading predictions due to epistemic uncertainty and aleatoric uncertainty, thus existing methods that rely solely on the output probabilities may fail to distinguish confident samples. Inspired by our observations, we propose an Uncertainty-aware Label Correction framework(ULC) to handle label noise on imbalanced datasets. First, we perform epistemic uncertainty-aware class-specific noise modeling to identify trustworthy clean samples and refine/discard highly confident true/corrupted labels.Then, we introduce aleatoric uncertainty in the subsequent learning process to prevent noise accumulation in the label noise modeling process. We conduct experiments on several synthetic and real-world datasets. The results demonstrate the effectiveness of the proposed method, especially on imbalanced datasets.

poster session 2 @ blue 2, poster session 9 @ blue 2, poster session 2, poster session 9

Active learning can be defined as iterations of data labeling, model training, and data acquisition, until sufficient labels are acquired. A traditional view of data acquisition is that, through iterations, knowledge from human labels and models is implicitly distilled to monotonically increase the accuracy and label consistency. Under this assumption, the most recently trained model is a good surrogate for the current labeled data, from which data acquisition is requested based on uncertainty/diversity. Our contribution is debunking this myth and proposing a new objective for distillation. First, we found example forgetting, which indicates the loss of knowledge learned across iterations. Second, for this reason, the last model is no longer the best teacher-- For mitigating such forgotten knowledge, we select one of its predecessor models as a teacher, by our proposed notion of "consistency". We show that this novel distillation is distinctive in the following three aspects; First, consistency ensures to avoid forgetting labels. Second, consistency improves both uncertainty/diversity of labeled data. Lastly, consistency redeems defective labels produced by human annotators.

poster session 2 @ blue 2, poster session 9 @ blue 2, poster session 2, poster session 9

Data augmentation is an efficient way to elevate 3D object detection performance. In this paper, we propose a simple but effective online crop-and-paste data augmentation pipeline for structured 3D point cloud scenes, named CorrelaBoost. Observing that 3D objects should have reasonable relative positions in a structured scene because of the objects' functionalities and natural relationships, we express this correlation as a kind of interactive force. An energy field called Correlation Field can be calculated correspondingly across the whole 3D space. According to the Correlation Field, we propose two data augmentation strategies to explore highly congruent positions that a designated object may be pasted to: 1) Category Consistent Exchanging and 2) Energy Optimized Transformation. We conduct exhaustive experiments on various popular benchmarks with different detection frameworks and the results illustrate that our method brings huge free-lunch improvement and significantly outperforms state-of-the-art approaches in terms of data augmentation. It is worth noting that the performance of VoteNet with mAP@0.5 is improved by 7.7 on ScanNetV2 dataset and 5.0 on SUN RGB-D dataset. Our method is simple to implement and increases few computational overhead.

poster session 2 @ red 3, poster session 9 @ red 3, poster session 2, poster session 9

To solve optimization problems with nonlinear constrains, the recently developed Riemannian meta-optimization methods show promise, which train neural networks as an optimizer to perform optimization on Riemannian manifolds. A key challenge is the heavy computational and memory burdens, because computing the meta-gradient with respect to the optimizer involves a series of time-consuming derivatives, and stores large computation graphs in memory. In this paper, we propose an efficient Riemannian meta-optimization method that decouples the complex computation scheme from the meta-gradient. We derive Riemannian implicit differentiation to compute the meta-gradient by establishing a link between Riemannian optimization and the implicit function theorem. As a result, the updating our optimizer is only related to the final two iterations, which in turn speeds up our method and reduces the memory footprint significantly. We theoretically study the computational load and memory footprint of our method for long optimization trajectories, and conduct an empirical study to demonstrate the benefits of the proposed method. Evaluations of three optimization problems on different Riemannian manifolds show that our method achieves state-of-the-art performance in terms of the convergence speed and the quality of optima.

poster session 2 @ blue 1, poster session 9 @ blue 1, oral session 2 @ blue 1, poster session 2, poster session 9, oral session 2

The need to understand the inner workings of opaque Machine Learning models has prompted researchers to devise various types of post-hoc explanations. A large class of such explainers proceed in two phases: first perturb an input instance whose explanation is sought, and then generate an interpretable artifact to explain the prediction of the opaque model on that instance. Recently, Deutch and Frost proposed to use an additional input from the user: a set of constraints over the input space to guide the perturbation phase. While this approach affords the user the ability to tailor the explanation to their needs, striking a balance between flexibility, theoretical rigor and computational cost has remained an open challenge. We propose a novel constraint-driven explanation generation approach which simultaneously addresses these issues in a modular fashion. Our framework supports the use of expressive Boolean constraints giving the user more flexibility to specify the subspace to generate perturbations from. Leveraging advances in Formal Methods, we can theoretically guarantee strict adherence of the samples to the desired distribution. This also allows us to compute fidelity in a rigorous way, while scaling much better in practice. Our empirical study demonstrates concrete uses of our tool CLIME in obtaining more meaningful explanations with high fidelity.

poster session 4 @ blue 3, poster session 9 @ blue 3, oral session 4 @ blue 3, poster session 4, poster session 9, oral session 4

Modern recommendation systems are mostly based on implicit feedback data which can be quite noisy due to false positives (FPs) caused by many reasons, such as misclicks or quick curiosity. Numerous recommendation algorithms based on collaborative filtering have leveraged post-click user behavior (e.g., skip) to identify false positives. They effectively involved these false positives in the model supervision as negative-like signals. Yet, false positives had not been considered in existing session-based recommendation systems (SBRs) although they provide just as deleterious effects. To resolve false positives in SBRs, we first introduce FP-Metric model which reformulates the objective of the session-based recommendation with FP constraints into metric learning regularization. In addition, we propose FP-AdaMetric that enhances the metric-learning regularization terms with an adaptive module that elaborately calculates the impact of FPs inside sequential patterns. We verify that FP-AdaMetric improves several session-based recommendation models' performances in terms of Hit Rate (HR), MRR, and NDCG on datasets from different domains including music, movie, and game. Furthermore, we show that the adaptive module plays a much more crucial role in FP-AdaMetric model than in other baselines.

poster session 5 @ blue 5, poster session 9 @ blue 5, poster session 5, poster session 9

In this paper, we study the problem of eliciting preferences of agents in the house allocation model. For this we build on a recent model of Hosseini et al.[AAAI’21] and focus on the task of eliciting preferences to find matchings which are necessarily optimal, i.e., optimal under all possible completions of the elicited preferences. In particular, we follow the approach of Hosseini et al. and investigate the elicitation of necessarily Pareto optimal (NPO) and necessarily rank-maximal (NRM) matchings. Most importantly, we answer their open question and give an online algorithm for eliciting an NRM matching in the next-best query model which is 3/2-competitive,i.e., it takes at most 3/2 as many queries as an optimal algorithm. Besides this, we extend this field of research by introducing two new natural models of elicitation and by studying both the complexity of determining whether a necessarily optimal matching exists in them, and by giving online algorithms for these models.

poster session 4 @ blue 6, poster session 9 @ blue 6, oral session 4 @ blue 6, poster session 4, poster session 9, oral session 4

Learning a disentangled representation is still a challenge in the field of the interpretability of generative adversarial networks (GANs). This paper proposes a generic method to modify a traditional GAN into an interpretable GAN, which ensures that filters in an intermediate layer of the generator encode disentangled localized visual concepts. Each filter in the layer is supposed to consistently generate image regions corresponding to the same visual concept when generating different images. The interpretable GAN learns to automatically discover meaningful visual concepts without any annotations of visual concepts. The interpretable GAN enables people to modify a specific visual concept on generated images by manipulating feature maps of the corresponding filters in the layer. Our method can be broadly applied to different types of GANs. Experiments have demonstrated the effectiveness of our method. The code will be released when the paper is accepted.

poster session 2 @ red 2, poster session 9 @ red 2, oral session 9 @ red 2, poster session 2, poster session 9, oral session 9

Recent advances in semi-supervised object detection (SSOD) are largely driven by consistency-based pseudo-labeling methods for image classification tasks, producing pseudo labels as supervisory signals. However, when using pseudo labels, there is a lack of consideration in localization precision and amplified class imbalance, both of which are critical for detection tasks. In this paper, we introduce certainty-aware pseudo labels tailored for object detection, which can effectively estimate the classification and localization quality of derived pseudo labels. This is achieved by converting conventional localization as a classification task followed by refinement. Conditioned on classification and localization quality scores, we dynamically adjust the thresholds used to generate pseudo labels and reweight loss functions for each category to alleviate the class imbalance problem. Extensive experiments demonstrate that our method improves state-of-the-art SSOD performance by 1-2% AP on COCO and PASCAL VOC while being orthogonal and complementary to most existing methods. In the limited-annotation regime, our approach improves supervised baselines by up to 10% AP using only 1-10% labeled data from COCO.

poster session 2 @ blue 2, poster session 9 @ blue 2, poster session 2, poster session 9

Aside the high performance of graph neural networks (GNNs), considerable attention has recently been paid to explanations of black-box deep learning models. Unlike most studies focusing on model explanations based on a specific graph instance, we propose Prototype-bAsed GNN-Explainer (PAGE), a novel model-level explanation method for graph-level classification that explains what the underlying model has learned by providing human-interpretable prototypes. Specifically, our method performs clustering on the embedding space of the underlying GNN model; extracts embeddings in each cluster; and discovers prototypes, which serve as model explanations, by estimating the maximum common subgraph (MCS) from the extracted embeddings. Experimental evaluation demonstrates that PAGE not only provides high-quality explanations but also outperforms the state-of-the-art model-level method in terms of consistency and faithfulness that are performance metrics for quantitative evaluations.

poster session 2 @ blue 2, poster session 9 @ blue 2, poster session 2, poster session 9

Building a socially intelligent agent involves many challenges, one of which is to teach the agent to speak guided by its value like a human. However, value-driven chatbots are still understudied in the area of dialogue systems. Most existing datasets focus on commonsense reasoning or social norm modeling. In this work, we present a new large-scale human value dataset called ValueNet, which contains human attitudes on 21,374 text scenarios. The dataset is organized in ten dimensions that conform to the basic human value theory in intercultural research. We further develop a Transformer-based value regression model on ValueNet to learn the utility distribution. Comprehensive empirical results show that the learned value model could benefit a wide range of dialogue tasks. For example, by teaching a generative agent with reinforcement learning and the rewards from the value model, our method attains state-of-the-art performance on the personalized dialog generation dataset: Persona-Chat. With values as additional features, existing emotion recognition models enable capturing rich human emotions in the context, which further improves the empathetic response generation performance in the EmpatheticDialogues dataset. To the best of our knowledge, ValueNet is the first large-scale text dataset for human value modeling, and we are the first one trying to incorporate a value model into emotionally intelligent dialogue systems. The dataset is available at https://liang-qiu.github.io/ValueNet/.

poster session 2 @ red 2, poster session 9 @ red 2, poster session 2, poster session 9

We introduce a new task of entailment-relation-aware paraphrase generation which aims at generating a paraphrase conforming to a given entailment relation (e.g. equivalent, forward entailing, or reverse entailing) with respect to the given input. We propose a reinforcement learning based weakly-supervised paraphrasing system, ERAP, that can be trained using existing paraphrase and natural language inference (NLI) corpora without an explicit task-specific corpus. A combination of automated and human evaluations show that ERAP generates paraphrases conforming to the specified entailment relation and are of good quality compared to baseline and uncontrolled paraphrasing systems. Using ERAP for augmenting training data for downstream textual entailment tasks improves performance over an uncontrolled paraphrasing system, and introduces fewer training artifacts, indicating the benefit of explicit control during paraphrasing.

poster session 6 @ red 5, poster session 9 @ red 5, poster session 6, poster session 9

In this paper, we propose a novel query design for the transformer-based object detection. In previous transformer-based detectors, the object queries are a set of learned embeddings. However, each learned embedding does not have an explicit physical meaning and we cannot explain where it will focus on. It is difficult to optimize as the prediction slot of each object query does not have a specific mode. In other words, each object query will not focus on a specific region. To solved these problems, in our query design, object queries are based on anchor points, which are widely used in CNN-based detectors. So each object query focuses on the objects near the anchor point. Moreover, our query design can predict multiple objects at one position to solve the difficulty: ``one region, multiple objects''. In addition, we design an attention variant, which can reduce the memory cost while achieving similar or better performance than the standard attention in DETR. Thanks to the query design and the attention variant, the proposed detector that we called Anchor DETR, can achieve better performance and run faster than the DETR with 10$\times$ fewer training epochs. For example, it achieves 44.2 AP with 19 FPS on the MSCOCO dataset when using the ResNet50-DC5 feature for training 50 epochs. Extensive experiments on the MSCOCO benchmark prove the effectiveness of the proposed methods. Code is available at \url{https://github.com/megvii-research/AnchorDETR}.

poster session 2 @ red 3, poster session 9 @ red 3, poster session 2, poster session 9

In the last decade, the blossom of deep learning has witnessed the rapid development of scene text recognition. However, the recognition of low-resolution scene text images remains a challenge. Even though some super-resolution methods have been proposed to tackle this problem, they usually treat text images as general images while ignoring the fact that the visual quality of strokes (the atomic unit of text) plays an essential role for text recognition. According to Gestalt Psychology, humans are capable of composing parts of details into the most similar objects guided by prior knowledge. Likewise, when humans observe a low-resolution text image, they will inherently use partial stroke-level details to recover the appearance of holistic characters. Inspired by Gestalt Psychology, we put forward a Stroke-Aware Scene Text Image Super-Resolution method containing a Stroke-Focused Module (SFM) to concentrate on stroke-level internal structures of characters in text images. Specifically, we attempt to design rules for decomposing English characters and digits at stroke-level, then pre-train a text recognizer to provide stroke-level attention maps as positional clues with the purpose of controlling the consistency between the generated super-resolution image and high-resolution ground truth. The extensive experimental results validate that the proposed method can indeed generate more distinguishable images on TextZoom and manually constructed Chinese character dataset Degraded-IC13. Furthermore, since the proposed SFM is only used to provide stroke-level guidance when training, it will not bring any time overhead during the test phase. Code is available at https://github.com/FudanVI/FudanOCR/tree/main/text-gestalt.

poster session 2 @ red 4, poster session 9 @ red 4, poster session 2, poster session 9

When humans collaborate with each other, they often make decisions by observing others and considering the consequences that their actions may have on the entire team, instead of greedily doing what is best for just themselves. We would like our AI agents to effectively collaborate in a similar way by capturing a model of their partners. In this work, we propose and analyze a decentralized Multi-Armed Bandit (MAB) problem with coupled rewards as an abstraction of more general multi-agent collaboration. We demonstrate that naive extensions of single-agent optimal MAB algorithms fail when applied for decentralized bandit teams. Instead, we propose a Partner-Aware strategy for joint sequential decision-making that extends the well-known single-agent Upper Confidence Bound algorithm. We analytically show that our proposed strategy achieves logarithmic regret, and provide extensive experiments involving human-AI and human-robot collaboration to validate our theoretical findings. Our results show that the proposed partner-aware strategy outperforms other known methods, and our human subject studies suggest humans prefer to collaborate with AI agents implementing our partner-aware strategy.

poster session 2 @ red 2, poster session 9 @ red 2, oral session 2 @ red 2, poster session 2, poster session 9, oral session 2

Implementations of artificial intelligence (AI) based on deep learning (DL) have proven to be highly successful in many domains, from biomedical imaging to natural language processing, but are still rarely applied in the space industry, particularly for onboard learning of planetary surfaces. In this project, we discuss the utility and limitations of DL, enhanced with topological footprints of the sensed objects, for multi-class classification of planetary surface patterns, in conjunction with tactile and embedded sensing in rover exploratory missions. We consider a Topological Convolutional Network (TCN) model with a persistence-based attention mechanism for supervised classification of various landforms. We study TCN's performance on the Barefoot surface pattern dataset, a novel surface pressure dataset from a prototype tactile rover wheel, known as the Barefoot Rover tactile wheel. Multi-class pattern recognition in the Barefoot data has neither been ever tackled before with DL nor assessed with topological methods. We provide insights into advantages and restrictions of topological DL as the early-stage concept for onboard learning and planetary exploration.

poster session 1 @ red 6, poster session 9 @ red 6, poster session 1, poster session 9

Algorithmic fairness is typically studied from the perspective of predictions. Instead, here we investigate fairness from the perspective of recourse actions suggested to individuals to remedy an unfavourable classification. We propose two new fair-ness criteria at the group and individual level, which—unlike prior work on equalising the average group-wise distance from the decision boundary—explicitly account for causal relationships between features, thereby capturing downstream effects of recourse actions performed in the physical world. We explore how our criteria relate to others, such as counterfactual fairness, and show that fairness of recourse is complementary to fairness of prediction. We study theoretically and empirically how to enforce fair causal recourse by altering the classifier and perform a case study on the Adult dataset. Finally, we discuss whether fairness violations in the data generating process revealed by our criteria may be better addressed by societal interventions as opposed to constraints on the classifier.

poster session 4 @ blue 3, poster session 9 @ blue 3, oral session 9 @ blue 3, poster session 4, poster session 9, oral session 9

Micronutrient deficiency (MND), which is a form of malnutrition that can have serious health consequences, is difficult to diagnose in early stages without blood draws, which are expensive and time-consuming to collect and process. It is even more difficult at a public health scale seeking to identify regions at higher risk of MND. To provide data more widely and frequently, we propose an accurate, scalable, low-cost, and interpretable regional-level MND prediction system. Specifically, our work is the first to use satellite data, such as forest cover, weather, and presence of water, to predict deficiency of micronutrients such as iron, Vitamin B12, and Vitamin A, directly from their biomarkers. We use real-world, ground truth biomarker data collected from four different regions across Madagascar for training, and demonstrate that satellite data are viable for predicting regional-level MND, surprisingly exceeding the performance of baseline predictions based only on survey responses. Our method could be broadly applied to other countries where satellite data are available, and potentially create high societal impact if these predictions are used by policy makers, public health officials, or healthcare providers.

poster session 4 @ red 6, poster session 9 @ red 6, poster session 4, poster session 9

We consider the problem of reducing the false discovery rate in multiple high-dimensional interventional datasets under unknown intervention targets when the time efficiency is acceptable. Traditional algorithms merged directly multiple causal DAGs learned, which ignores the contradictions of different datasets, leading to lots of contradictory directions of edges. For reducing the contradictory information, we propose a new algorithm, which first learns an intervention Markov equivalence class (I-MEC) before merging multiple causal DAGs. It utilizes the full power of the constraints available in interventional data and combines ideas from local learning, intervention, and search-and-score techniques in a principled and effective way in different intervention experiments. Specifically, local learning on multiple datasets is used to build a causal skeleton. Perfect intervention destroys some possible triangles and obtains more V-structures, getting a theoretically correct I-MEC. Search and scoring techniques based on the learned I-MEC further identify the remaining unoriented edges. Experiments on benchmark Bayesian networks with the number of variables from 20 to 724 validate that the effectiveness of our algorithm in reducing the false discovery rate in high-dimensional interventional data.

poster session 4 @ blue 3, poster session 9 @ blue 3, poster session 4, poster session 9

Spiking Neural Networks (SNNs) have been attached great importance due to the distinctive properties of low power consumption, biological plausibility, and adversarial robustness. The most effective way to train deep SNNs is through ANN-to-SNN conversion, which have yielded the best performance in deep network structure and large-scale datasets. However, there is a trade-off between accuracy and latency. In order to achieve high precision as original ANNs, a long simulation time is needed to match the firing rate of a spiking neuron with the activation value of an analog neuron, which impedes the practical application of SNN. In this paper, we aim to achieve high-performance converted SNNs with extremely low latency (fewer than 32 time-steps). We start by theoretically analyzing ANN-to-SNN conversion and show that scaling the thresholds does play a similar role as weight normalization. Instead of introducing constraints that facilitate ANN-to-SNN conversion at the cost of model capacity, we applied a more direct way by optimizing the initial membrane potential to reduce the conversion loss in each layer. Besides, we demonstrate that optimal initialization of membrane potentials can implement expected error-free ANN-to-SNN conversion. We evaluate our algorithm on the CIFAR-10 dataset and CIFAR-100 dataset and achieve state-of-the-art accuracy, using fewer time-steps. For example, we reach top-1 accuracy of 93.38% on CIFAR-10 with 16 time-steps. Moreover, our method can be applied to other ANN-SNN conversion methodologies and remarkably promote performance when the time-steps is small.

poster session 2 @ red 2, poster session 9 @ red 2, poster session 2, poster session 9

In recent years, optical flow methods develop rapidly, achieving unprecedented high performance. Most of the methods only consider single-modal optical flow under the well-known brightness-constancy assumption. However, in many application systems, images of different modalities need to be aligned, which demands to estimate cross-modal flow between the cross-modal image pairs. A lot of cross-modal matching methods are designed for some specific cross-modal scenarios. We argue that the prior knowledge of the advanced optical flow models can be transferred to the cross-modal flow estimation, which may be a simple but unified solution for diverse cross-modal matching tasks. To verify our hypothesis, we design a self-supervised framework to promote the single-modal optical flow networks for diverse corss-modal flow estimation. Moreover, we add a Cross-Modal-Adapter block as a plugin to the state-of-the-art optical flow model RAFT for better performance in cross-modal scenarios. Our proposed Modality Promotion Framework and Cross-Modal Adapter have multiple advantages compared to the existing methods. The experiments demonstrate that our method is effective on multiple datasets of different cross-modal scenarios.

poster session 5 @ red 1, poster session 9 @ red 1, oral session 9 @ red 1, poster session 5, poster session 9, oral session 9

Corrupted labels and class imbalance are commonly encountered in practically collected training data, which easily leads to over-fitting of deep neural networks (DNNs). Existing approaches alleviate these issues by adopting a sample re-weighting strategy, which are designed weighting function mapping training loss to sample weight. However, it is only applicable for training data containing only either one type of data biases. In practice, however, biased samples with corrupted labels and of tailed classes commonly co-exist in training data, how to handle them simultaneously is a key but under-explored problem. In this paper, we found that these two types of biased samples, though have similar transient loss, have distinguishable trend and characteristics in loss curves, which could provide valuable priors for sample weight assignment. Motivated by this, we delve into the loss curves and propose a novel probe-and-allocate training strategy: In the probing stage, we train the network on the whole biased training data without intervention, and record the loss curve of each sample as an additional attribute; In the allocating stage, we feed the resulting attribute to a newly designed curve-perception network, named CurveNet, to learn to identify the bias type of each sample and assign proper weights through meta-learning adaptively. To the best of our knowledge, we are the first to simultaneously handle corrupted labels and class imbalance existing in training data. Extensive synthetic and real experiments well validate the proposed method, which achieves state-of-the-art performance on multiple challenging benchmarks.

poster session 2 @ blue 2, poster session 9 @ blue 2, poster session 2, poster session 9

The CO2 capture efficiency in solvent-based carbon capture systems (CCSs) critically depends on the gas-solvent interfacial area (IA), making maximization of IA a foundational challenge in CCS design. While the IA associated with a particular CCS design can be estimated via a computational fluid dynamics (CFD) simulation, using CFD to derive the IAs associated with numerous CCS designs is prohibitively costly. Fortunately, previous works such as Deep Fluids (DF) (Kim et al., 2019) show that large simulation speedups are achievable by replacing CFD simulators with neural network (NN) surrogates that faithfully mimic the CFD simulation process. This raises the possibility of a fast, accurate replacement for a CFD simulator and therefore efficient approximation of the IAs required by CCS design optimization. Thus, here, we build on the DF approach to develop surrogates that can successfully be applied to our complex carbon-capture CFD simulations. Our optimized DF-style surrogates produce large speedups (4000x) while obtaining IA relative errors as low as 4% on unseen CCS configurations that lie within the range of training configurations. This hints at the promise of NN surrogates for our CCS design optimization problem. Nonetheless, DF has inherent limitations with respect to CCS design (e.g., limited transferability of trained models to new CCS packings). We conclude with ideas to address these challenges.

poster session 1 @ red 6, poster session 9 @ red 6, poster session 1, poster session 9

The Maximum $k$-Defective Clique Problem (MDCP), as a clique relaxation model, has been used to solve various problems. Because it is a computational hard task, previous works can hardly solve the MDCP for massive sparse graphs derived from real-world applications. In this work, we propose a novel branch-and-bound algorithm to solve the MDCP based on several new techniques. First, we propose two new upper bounds of the MDCP as well as corresponding reduction rules to remove redundant vertices and edges. The proposed reduction rules are particularly useful for massive graphs. Second, we present another new upper bound by counting missing edges between fixed vertices and an unfixed vertex for cutting branches. We perform extensive computational experiments to evaluate our algorithm. Experimental results show that our reduction rules are very effective for removing redundant vertices and edges so that graphs are reduced greatly. Also, our algorithm can solve benchmark instances efficiently, and it has significantly better performance than state-of-the-art algorithms.

poster session 2 @ blue 4, poster session 9 @ blue 4, oral session 2 @ blue 4, poster session 2, poster session 9, oral session 2

Low-frequency word prediction remains a challenge in modern neural machine translation (NMT) systems. Recent adaptive training methods promote the output of infrequent words by emphasizing their weights in the overall training objectives. Despite the improved recall of low-frequency words, their prediction precision is unexpectedly hindered by the adaptive objectives. Inspired by the observation that low-frequency words form a more compact embedding space, we tackle this challenge from a representation learning perspective. Specifically, we propose a frequency-aware token-level contrastive learning method, in which the hidden state of each decoding step is pushed away from the counterparts of other target words, in a soft contrastive way based on the corresponding word frequencies. We conduct experiments on widely used NIST Chinese-English and WMT14 English-German translation tasks. Empirical results show that our proposed methods can not only significantly improve the translation quality but also enhance lexical diversity and optimize word representation space. Further investigation reveals that, comparing with related adaptive training strategies, the superiority of our method on low-frequency word prediction lies in the robustness of token-level recall across different frequencies without sacrificing precision.

poster session 6 @ red 5, poster session 9 @ red 5, poster session 6, poster session 9

In recent years, proposed studies on time-series anomaly detection (TAD) report high F1 scores on benchmark TAD datasets, giving the impression of clear improvements. However, most studies apply a peculiar evaluation protocol called point adjustment (PA) before scoring. In this paper, we theoretically and experimentally reveal that the PA protocol has a great possibility of overestimating the detection performance; that is, even a random anomaly score can easily turn into a state-of-the-art TAD method. Therefore, the comparison of TAD methods with after applying PA protocol can lead to misguided rankings. Furthermore, we question the potential of existing TAD methods by showing that an untrained model obtains comparable detection performance to the existing methods even when PA is forbidden. Based on our findings, we propose a new baseline and an evaluation protocol. We expect that our study will help a rigorous evaluation of TAD and lead to further improvement in future researches.

poster session 2 @ blue 1, poster session 9 @ blue 1, poster session 2, poster session 9

Conventional saliency prediction models typically learn a deterministic mapping from images to the corresponding ground truth saliency maps. In this paper, we study the saliency prediction problem from the perspective of generative models by learning a conditional probability distribution over saliency maps given an image, and treating the saliency prediction as a sampling process. Specifically, we propose a generative cooperative saliency prediction framework, where a conditional latent variable model and a conditional energy-based model are jointly trained to predict saliency in a cooperative manner. The latent variable model serves as a fast but coarse predictor to efficiently produce an initial prediction, which is then refined by the iterative Langevin revision of the energy-based model that serves as a fine predictor. Such a coarse-to-fine cooperative saliency prediction strategy offers the best of both worlds. We further generalize our framework to weakly supervised saliency prediction with a cooperative learning while recovering strategy. Experimental results show that our generative model achieves both state-of-the-art performance and reliable sampling processing exploring.

poster session 2 @ red 2, poster session 9 @ red 2, oral session 9 @ red 2, poster session 2, poster session 9, oral session 9

Emotion detection from face is an important problem and has received attention from industry and academia. Although emotion recognition from videos has a very high performance, emotion recognition from a single image stays a challenging task. In this paper, we try to use information from videos to do emotion recognition on a single image. More specifically, we leverage contrastive loss for pretraining the network on the videos and experiment with different sampling methods to select consistently hard triplets for continual learning of the network. Once the embeddings have been trained, we test them on a standard emotion classification task. Our method significantly improves the performance of the models and shows the efficacy of self-supervision in emotion recognition.

poster session 5 @ red 1, poster session 9 @ red 1, poster session 5, poster session 9

The key to semi-supervised learning (SSL) is to explore adequate information to leverage the unlabeled data. Current dominant approaches aim to generate pseudo-labels on weakly augmented instances and train models on their corresponding strongly augmented variants with high-confidence results. However, such methods are limited in excluding samples with low-confidence pseudo-labels and under-utilization of the label information. In this paper, we emphasize the cruciality of the label information and propose a Label-guided Self-training approach to Semi-supervised Learning (LaSSL), which improves pseudo-label generations from two mutually boosted strategies. Firstly, with the ground-truth labels and iteratively-polished pseudo-labels, we explore instance relations among all samples and then minimize a class-aware contrastive loss to learn discriminative feature representations that make same-class samples gathered and different-class samples scattered. Second, on top of improved feature representations, we propagate the label information to the unlabeled samples across the potential data manifold at the feature-embedding level, which can further improve the labelling of samples with reference to their neighbours. These two strategies are seamlessly integrated and mutually promoted across the whole training process. We evaluate LaSSL on several classification benchmarks under partially labeled settings and demonstrate its superiority over the state-of-the-art approaches.

poster session 2 @ blue 2, poster session 9 @ blue 2, oral session 2 @ blue 2, poster session 2, poster session 9, oral session 2

Random forests have long been considered as powerful model ensembles in machine learning. By training multiple decision trees, whose diversity is fostered through data and feature subsampling, the resulting random forest can lead to more stable and reliable predictions than a single decision tree. This however comes at the cost of decreased interpretability: while decision trees are often easily interpretable, the predictions made by random forests are much more difficult to understand, as they involve a majority vote over multiple decision trees. In this paper, we examine different types of reasons that explain “why” an input instance is classified as positive or negative by a Boolean random forest. Notably, as an alternative to prime-implicant explanations taking the form of subset-minimal implicants of the random forest, we introduce majoritary reasons which are subset-minimal implicants of a strict majority of decision trees. For these abductive explanations, the tractability of the generation problem (finding one reason) and the optimization problem (finding one shortest reason) are investigated. Experiments conducted on various datasets reveal the existence of a trade-off between runtime complexity and sparsity. In practice, prime-implicant explanations - for which the identification problem is DP-complete - are slightly larger than majoritary reasons that can be generated using a simple linear-time greedy algorithm. They are also significantly larger than minimum-size majoritary reasons which can be approached using an anytime PARTIAL MAXSAT algorithm.

poster session 4 @ blue 3, poster session 9 @ blue 3, oral session 4 @ blue 3, poster session 4, poster session 9, oral session 4

Learning and generalizing from limited examples, i.e., few-shot learning, is of core importance to many real-world vision applications. A principal way of achieving few-shot learning is to realize an embedding where samples from different classes are distinctive. Recent studies suggest that embedding via hyperbolic geometry enjoys low distortion for hierarchical and structured data, making it suitable for few-shot learning. In this paper, we propose to learn a context-aware hyperbolic metric to characterize the distance between a point and a set associated with a learned set to set distance. To this end, we formulate the metric as a weighted sum on the tangent bundle of the hyperbolic space and develop a mechanism to obtain the weights adaptively, based on the constellation of the points. This not only makes the metric local but also dependent on the task in hand, meaning that the metric will adapt depending on the samples that it compares. We empirically show that such metric yields robustness in the presence of outliers and achieves a tangible improvement over baseline models. This includes the state-of-the-art results on five popular few-shot classification benchmarks, namely mini-ImageNet, tiered-ImageNet, Caltech-UCSD Birds-200-2011(CUB), CIFAR-FS, and FC100.

poster session 2 @ red 2, poster session 9 @ red 2, poster session 2, poster session 9

To interpret uncertainty estimates from differentiable probabilistic models, recent work has proposed generating a single Counterfactual Latent Uncertainty Explanation (CLUE) for a given data point where the model is uncertain. We broaden the exploration to examine δ-CLUE, the set of potential CLUEs within a δ ball of the original input in latent space. We study the diversity of such sets and find that many CLUEs are redundant; as such, we propose DIVerse CLUE (∇-CLUE), a set of CLUEs which each propose a distinct explanation as to how one can decrease the uncertainty associated with an input. We then further propose GLobal AMortised CLUE (GLAM-CLUE), a distinct, novel method which learns amortised mappings that apply to specific groups of uncertain inputs, taking them and efficiently transforming them in a single function call into inputs for which a model will be certain. Our experiments show that δ-CLUE, ∇-CLUE, and GLAM-CLUE all address shortcomings of CLUE and provide beneficial explanations of uncertainty estimates to practitioners.

poster session 4 @ blue 3, poster session 9 @ blue 3, poster session 4, poster session 9

Recently, many regression based conditional independence (CI) test methods have been proposed to solve the problem of causal discovery. These methods provide alternatives to test CI of $x,y$ given $Z$ by first removing the information of controlling set $Z$ from $x$ and $y$, and then testing the independence between two residuals $R_{x,Z}$ and $R_{y,Z}$. When these residuals are linearly uncorrelated, the independence test between residuals is nontrivial. With the ability to calculate inner product in high-dimensional space, kernel-based methods are usually used to achieve this goal, but still consume considerable time. In this paper, we investigate the independence between two linear combinations under linear non-Gaussian structural equation model. We show that the dependence between two residuals $R_{x,Z}$ and $R_{y,Z}$ can be captured by the difference between the similarity of $(R_{x,Z},R_{y,Z})$ and that of $(R_{x,Z},R_{r})$ ($R_{r}$ is an independent copy of $R_{y,Z}$) in high-dimensional space. With this result, we design a new method called SCIT for CI test, where permutation test is performed to control Type I error rate. The proposed method is simpler yet more efficient and effective than the existing ones. When applied to causal discovery, the proposed method outperforms the counterparts in terms of both speed and Type II error rate, especially in the case of small sample size, which is validated by our extensive experiments on both synthetic and real-world datasets.

poster session 4 @ blue 3, poster session 9 @ blue 3, poster session 4, poster session 9

We present YOFO (You Only inFer Once), a new paradigm for referring video object segmentation (RVOS) that operates in a one-stage manner. Our key insight is that the language descriptor should serve as a target-specific guidance to identify the target object, while a direct feature fusion of image and language can increase feature complexity and thus may be sub-optimal for RVOS. To this end, we propose a meta-transfer module, which is trained in a learning-to-learn fashion and aims to transfer the target-specific information from the language domain to the image domain, while discarding the uncorrelated complex variations of language description. To bridge the gap between the image and language domains, we develop a multi-scale cross-modal feature mining block, which aggregates all the essential features required by RVOS from both two domains and generates regression labels for the meta-transfer module. The whole system can be trained in an end-to-end manner and outperforms state-of-the-art two-stage approaches.

poster session 2 @ red 4, poster session 9 @ red 4, poster session 2, poster session 9

In this paper, we introduce a multi-armed bandit problem termed max-min grouped bandits, in which the arms are arranged in possibly-overlapping groups, and the goal is to find a group whose worst arm has the highest mean reward. This problem is of interest in applications such as recommendation systems, and is also closely related to widely-studied robust optimization problems. We present two algorithms based successive elimination and robust optimization, and derive upper bounds on the number of samples to guarantee finding a max-min optimal or near-optimal group, as well as an algorithm-independent lower bound. We discuss the degree of tightness of our bounds in various cases of interest, and the difficulties in deriving uniformly tight bounds.

poster session 2 @ blue 1, poster session 9 @ blue 1, poster session 2, poster session 9

Graph representation learning received increasing attentions in recent years. Most of the existing methods ignore the complexity of the graph structures and restrict graphs in a single constant-curvature representation space, which is only suitable to particular kinds of graph structure indeed. Additionally, these methods follow the supervised or semi-supervised learning paradigm, and thereby notably limit their deployment on the unlabeled graphs in real applications. To address these aforementioned limitations, we take the first attempt to study the self-supervised graph representation learning in the mixed-curvature spaces. In this paper, we present a novel Self-supervised Mixed-curvature Graph Neural Network (SelfMGNN). Instead of working on one single constant-curvature space, we construct a mixed-curvature space via the Cartesian product of multiple Riemannian component spaces and design hierarchical attention mechanisms for learning and fusing the representations across these component spaces. To enable the self-supervisd learning, we propose a novel dual contrastive approach. The constructed mixed-curvature space actually provides multiple Riemannian views for the contrastive learning. We introduce a Riemannian projector to reveal these views, and utilize a well-designed Riemannian discriminator for the single-view and cross-view contrastive learning within and across the Riemannian views. Finally, extensive experiments show that SelfMGNN captures the complicated graph structures in reality and outperforms state-of-the-art baselines.

poster session 5 @ blue 5, poster session 9 @ blue 5, oral session 9 @ blue 5, poster session 5, poster session 9, oral session 9

We explore deep clustering of multilingual text representations for unsupervised model interpretation and induction of syntax. As these representations are high-dimensional, out-of-the-box methods like K-means do not work well. Thus, our approach jointly transforms the representations into a lower-dimensional cluster-friendly space and clusters them. We consider two notions of syntax: Part of Speech Induction (POSI) and Constituency Labelling (CoLab) in this work. Interestingly, we find that Multilingual BERT (mBERT) contains surprising amount of syntactic knowledge of English; possibly even as much as English BERT (E-BERT). Our model can be used as a supervision-free probe which is arguably a less-biased way of probing. We find that unsupervised probes show benefits from higher layers as compared to supervised probes. We further note that our unsupervised probe utilizes E-BERT and mBERT representations differently, especially for POSI. We validate the efficacy of our probe by demonstrating its capabilities as a unsupervised syntax induction technique. Our probe works well for both syntactic formalisms by simply adapting the input representations. We report competitive performance of our probe on 45-tag English POSI, state-of-the-art performance on 12-tag POSI across 10 languages, and competitive results on CoLab. We also perform zero-shot syntax induction on resource impoverished languages and report strong results.

poster session 6 @ red 5, poster session 9 @ red 5, poster session 6, poster session 9

This paper presents an end-to-end instance segmentation framework, termed SOIT, that Segments Objects with Instance-aware Transformers. Inspired by DETR, our method views instance segmentation as a direct set prediction problem and effectively removes the need for many hand-crafted components like RoI cropping, one-to-many label assignment, and non-maximum suppression (NMS). In SOIT, multiple queries are learned to directly reason a set of object embeddings of semantic category, bounding-box location, and pixel-wise mask in parallel under the global image context. The class and bounding-box can be easily embedded by a fixed-length vector. The pixel-wise mask, especially, is embedded by a group of parameters to construct a lightweight instance-aware transformer. Afterward, a full-resolution mask is produced by the instance-aware transformer without involving any RoI-based operation. Overall, SOIT introduces a simple single-stage instance segmentation framework that is both RoI- and NMS-free. Experimental results on the MS COCO dataset demonstrate that SOIT outperforms state-of-the-art instance segmentation approaches significantly. Moreover, the joint learning of multiple tasks in a unified query embedding can also substantially improve the detection performance. Code is available at https://github.com/yuxiaodongHRI/SOIT.

poster session 2 @ red 4, poster session 9 @ red 4, poster session 2, poster session 9

In this paper, we propose a new task of cross-modal federated human activity recognition (CMF-HAR), which is conducive to promote the large-scale use of the HAR model on more local devices. To address the new task, we propose a feature-disentangled activity recognition network (FDARN), which has five important modules of altruistic encoder, egocentric encoder, shared activity classifier, private activity classifier and modality discriminator. The altruistic encoder aims to collaboratively embed local instances on different clients into a modality-agnostic feature subspace. The egocentric encoder aims to produce modality-specific features that cannot be shared across clients with different modalities. The modality discriminator is used to adversarially guide the parameter learning of the altruistic and egocentric encoders. Through decentralized optimization with a spherical modality discriminative loss, our model can not only generalize well across different clients by leveraging the modality-agnostic features but also capture the modality-specific discriminative characteristics of each client. Extensive experiment results on four datasets demonstrate the effectiveness of our method.

poster session 5 @ red 1, poster session 9 @ red 1, oral session 5 @ red 1, poster session 5, poster session 9, oral session 5

Convolutional neural networks (CNNs) have been commonly applied in the area of the Electroencephalography (EEG)-based Motor Imagery (MI) classification, significantly pushing the boundary of the state-of-the-art. In order to simultaneously decode the discriminative features and eliminate the negative effects of non-Gaussian noise and outliers in the motor imagery data, in this abstract, we propose a novel robust supervision signal, called Correntropy based Center Loss (CCL), for CNN training, which utilizes the correntropy induced distance as the objective measure. It is encouraging to see that the CNN model trained by the combination of softmax loss and CCL loss outperforms the state-of-the-art models on two public datasets.

poster session 5 @ red 1, poster session 9 @ red 1, poster session 5, poster session 9

Effective decision making while competing for limited resources in adversarial environments is important for many real-world applications (e.g. two Taxi companies competing for customers). Decision-making techniques such as Automated planning have to take into account possible actions of adversary (or competing) agents. That said, the agent should know what the competitor will likely do and then generate its plan accordingly. In this paper we propose a novel approach for estimating strategies of the adversary (or the competitor), sampling its actions that might hinder agent's goals by interfering with the agent's actions. The estimated competitor strategies are used in plan generation such that agent's actions have to be applied prior to the ones of the competitor, whose estimated times dictate the deadlines. We empirically evaluate our approach leveraging sampling of competitor's actions by comparing it to the naive approach optimising the make-span (not taking the competing agent into account at all) and to Nash Equilibrium (mixed) strategies.

poster session 4 @ blue 6, poster session 9 @ blue 6, oral session 9 @ blue 6, poster session 4, poster session 9, oral session 9

Unlike traditional supervised learning, in many settings only partial feedback is available. We may only observe outcomes for the chosen actions, but not the counterfactual outcomes associated with other alternatives. Such settings encompass a wide variety of applications including pricing, online marketing and precision medicine. A key challenge is that observational data are influenced by historical policies deployed in the system, yielding a biased data distribution. We approach this task as a domain adaptation problem and propose a self-training algorithm which imputes outcomes with \textit{categorical} values for \textit{finite} unseen actions in the observational data to simulate a randomized trial through pseudolabelling, which we refer to as Counterfactual Self-Training (CST). CST iteratively imputes pseudolabels and retrains the model. In addition, we show input consistency loss can further improve CST performance which is shown in recent theoretical analysis of pseudolabelling. We demonstrate the effectiveness of the proposed algorithms on both synthetic and real datasets.

poster session 4 @ blue 3, poster session 9 @ blue 3, poster session 4, poster session 9

We develop a new method of online inference for a vector of parameters estimated by the Polyak-Ruppert averaging procedure of stochastic gradient descent (SGD) algorithms. We leverage insights from time series regression in econometrics and construct asymptotically pivotal statistics via random scaling. Our approach is fully operational with online data and is rigorously underpinned by a functional central limit theorem. Our proposed inference method has a couple of key advantages over the existing methods. First, the test statistic is computed in an online fashion with only SGD iterates and the critical values can be obtained without any resampling methods, thereby allowing for efficient implementation suitable for massive online data. Second, there is no need to estimate the asymptotic variance and our inference method is shown to be robust to changes in the tuning parameters for SGD algorithms in simulation experiments with synthetic data.

poster session 2 @ blue 2, poster session 9 @ blue 2, poster session 2, poster session 9

In this paper, a new deep learning network named as graph-based point tracker (GPT) is proposed for 3D object tracking in point clouds. GPT is not based on Siamese network applied to template and search area, but it is based on the transfer of target clue from the template to the search area. GPT is end-to-end trainable. GPT has two new modules: graph feature augmentation (GFA) and improved target clue (ITC) module. The key idea of GFA is to exploit one-to-many relationship between template and search area points using a bipartite graph. In GFA, edge features of the bipartite graph are generated by transferring the target clues of template points to search area points through edge convolution. It captures the relationship between template and search area points effectively from the perspective of geometry and shape of two point clouds. The second module is ITC. The key idea of ITC is to embed the information of the center of the target into the edges of the bipartite graph via Hough voting, strengthening the discriminative power of GFA. Both modules significantly contribute to the improvement of GPT by transferring geometric and shape information including target center from target template to search area effectively. Experiments on the KITTI tracking dataset show that GPT achieves state-of-the-art performance and can run in real-time.

poster session 5 @ red 1, poster session 9 @ red 1, poster session 5, poster session 9

Large deformations of organs, caused by diverse shapes and nonlinear shape changes, pose a significant challenge for medical image registration. Traditional registration methods need to iteratively optimize an objective function via a specific deformation model along with meticulous parameter tuning, but which have limited capabilities in registering images with large deformations. While deep learning-based methods can learn the complex mapping from input images to their respective deformation field, it is regression-based and is prone to be stuck at local minima, particularly when large deformations are involved. To this end, we present Stochastic Planner-Actor-Critic (spac), a novel reinforcement learning-based framework that performs step-wise registration. The key notion is warping a moving image successively by each time step to finally align to a fixed image. Considering that it is challenging to handle high dimensional continuous action and state spaces in the conventional reinforcement learning (RL) framework, we introduce a new concept `Plan' to the standard Actor-Critic model, which is of low dimension and can facilitate the actor to generate a tractable high dimensional action. The entire framework is based on unsupervised training and operates in an end-to-end manner. We evaluate our method on several 2D and 3D medical image datasets, some of which contain large deformations. Our empirical results highlight that our work achieves consistent, significant gains and outperforms state-of-the-art methods.

poster session 2 @ red 2, poster session 9 @ red 2, poster session 2, poster session 9

Various types of machine learning techniques are available for analyzing electronic health records (EHRs). For predictive tasks, most existing methods either explicitly or implicitly divide these time-series datasets into predetermined observation and prediction windows. Patients have different lengths of medical history and the desired predictions (for purposes such as diagnosis or treatment) are required at different times in the future. In this paper, we propose a method that uses a sequence-to-sequence generator model to transfer an input sequence of EHR data to a sequence of user-defined target labels, providing the end-users with ``flexible'' observation and prediction windows to define. We use adversarial and semi-supervised approaches in our design, where the sequence-to-sequence model acts as a generator and a discriminator distinguishes between the actual (observed) and generated labels. We evaluate our models through an extensive series of experiments using two large EHR datasets from adult and pediatric populations. In an obesity predicting case study, we show that our model can achieve superior results in flexible-window prediction tasks, after being trained once and even with large missing rates on the input EHR data. Moreover, using a number of attention analysis experiments, we show that the proposed model can effectively learn more relevant features in different prediction tasks.

poster session 4 @ red 6, poster session 9 @ red 6, poster session 4, poster session 9

Inferring spatial relations in natural language is a crucial ability an intelligent system should possess. The bAbI dataset tries to capture tasks relevant to this domain (task 17 and 19). However, these tasks have several limitations. Most importantly, they are limited to fixed expressions, they are limited in the number of reasoning steps required to solve them, and they fail to test the robustness of models to input that contains irrelevant or redundant information. In this paper, we present a new Question-Answering dataset called StepGame for robust multi-step spatial reasoning in texts. Our experiments demonstrate that state-of-the-art models on the bAbI dataset struggle on the StepGame dataset. Moreover, we propose a Tensor-Product based Memory-Augmented Neural Network (TP-MANN) specialized for spatial reasoning tasks. Experimental results on both datasets show that our model outperforms all the baselines with superior generalization and robustness performance.

poster session 6 @ red 5, poster session 9 @ red 5, oral session 9 @ red 5, poster session 6, poster session 9, oral session 9

Error propagation is a general but crucial problem in online semi-supervised video object segmentation. We aim to suppress error propagation through a correction mechanism with high reliability. The key insight is to disentangle the correction from the conventional mask propagation process with reliable cues. We introduce two modulators, propagation and correction modulators, to separately perform channel-wise recalibration on the target frame embeddings according to local temporal correlations and reliable references respectively. Specifically, we assemble the modulators with a cascaded propagation-correction scheme. This avoids overriding the effects of the reliable correction modulator by the propagation modulator. Although the reference frame with the ground truth label provides reliable cues, it could be very different from the target frame and introduce uncertain or incomplete correlations. We augment the reference cues by supplementing reliable feature patches to a maintained pool, thus offering more comprehensive and expressive object representations to the modulators. In addition, a reliability filter is designed to retrieve reliable patches and pass them in subsequent frames. Our model achieves state-of-the-art performance on YouTube-VOS18, YouTube-VOS19 and DAVIS17-Val/Test benchmarks. Extensive experiments demonstrate that the correction mechanism provides considerable performance gain by fully utilizing reliable guidance.

poster session 5 @ red 1, poster session 9 @ red 1, oral session 5 @ red 1, poster session 5, poster session 9, oral session 5

In online algorithm selection (OAS), instances of an algorithmic problem class are presented to an agent one after another, and the agent has to quickly select a presumably best algorithm from a fixed set of candidate algorithms. For decision problems such as satisfiability (SAT), quality typically refers to the algorithm's runtime. As the latter is known to exhibit a heavy-tail distribution, an algorithm is normally stopped when exceeding a predefined upper time limit. As a consequence, machine learning methods used to optimize an algorithm selection strategy in a data-driven manner need to deal with right-censored samples, a problem that has received little attention in the literature so far. In this work, we revisit multi-armed bandit algorithms for OAS and discuss their capability of dealing with the problem. Moreover, we adapt them towards runtime-oriented losses, allowing for partially censored data while keeping a space- and time-complexity independent of the time horizon. In an extensive experimental evaluation on an adapted version of the ASlib benchmark, we demonstrate that theoretically well-founded methods based on Thompson sampling perform specifically strong and improve in comparison to existing methods.

poster session 4 @ blue 6, poster session 9 @ blue 6, poster session 4, poster session 9

Singing voice synthesis (SVS) systems are built to synthesize high-quality and expressive singing voice, in which the acoustic model generates the acoustic features (\eg, mel-spectrogram) given a music score. Previous singing acoustic models adopt a simple loss (\eg, L1 and L2) or generative adversarial network (GAN) to reconstruct the acoustic features, while they suffer from over-smoothing and unstable training issues respectively, which hinder the naturalness of synthesized singing. In this work, we propose DiffSinger, an acoustic model for SVS based on the diffusion probabilistic model. DiffSinger is a parameterized Markov chain that iteratively converts the noise into mel-spectrogram conditioned on the music score. By implicitly optimizing variational bound, DiffSinger can be stably trained and generate realistic outputs. To further improve the voice quality and speed up inference, we introduce a shallow diffusion mechanism to make better use of the prior knowledge learned by the simple loss. Specifically, DiffSinger starts generation at a shallow step smaller than the total number of diffusion steps, according to the intersection of the diffusion trajectories of the ground-truth mel-spectrogram and the one predicted by a simple mel-spectrogram decoder. Besides, we propose boundary prediction methods to locate the intersection and determine the shallow step adaptively. The evaluations conducted on a Chinese singing dataset demonstrate that DiffSinger outperforms state-of-the-art SVS work. Extensional experiments also prove the generalization of our methods on text-to-speech task (DiffSpeech). Audio samples are available via \url{https://diffsinger.github.io}.

poster session 6 @ red 5, poster session 9 @ red 5, poster session 6, poster session 9

Training the multi-label image recognition models with partial labels, in which merely some labels are known while others are unknown for each image, is a considerably challenging and practical task. To address this task, current algorithms mainly depend on pre-training classification or similarity models to generate pseudo labels for the unknown labels. However, these algorithms depend on sufficient multi-label annotations to train the models, leading to poor performance especially with low known label proportion. In this work, we propose to blend category-specific representation across different images to transfer information of known labels to complement unknown labels, which can get rid of pre-training models and thus does not depend on sufficient annotations. To this end, we design a unified semantic-aware representation blending (SARB) framework that exploits instance-level and prototype-level semantic representation to complement unknown labels by two complementary modules: 1) an instance-level representation blending (ILRB) module blends the representations of the known labels in an image to the representations of the unknown labels in another image to complement these unknown labels. 2) a prototype-level representation blending (PLRB) module learns more stable representation prototypes for each category and blends the representation of unknown labels with the prototypes of corresponding labels to complement these labels. Extensive experiments on the MS-COCO, Visual Genome, Pascal VOC 2007 datasets show that the proposed SARB framework obtains superior performance over current leading competitors on all known label proportion settings, i.e., with the mAP improvement of 4.6%, 4.6%, 2.2% on these three datasets when the known label proportion is 10%. Codes are available at https://github.com/HCPLab-SYSU/SARB-MLR-PL.

poster session 2 @ red 3, poster session 9 @ red 3, poster session 2, poster session 9

Multi-task learning has been widely used in real-world recommenders to predict different types of user feedback. Most prior works focus on designing network architectures for bottom layers as a means to share the knowledge about input features representations. However, since they adopt task-specific binary labels as supervised signals for training, the knowledge about how to accurately rank items is not fully shared across tasks. In this paper, we aim to enhance knowledge transfer for multi-task personalized recommendat optimization objectives. We propose a Cross-Task Knowledge Distillation (CrossDistil) framework in recommendation, which consists of three procedures. 1) Task Augmentation: We introduce auxiliary tasks with quadruplet loss functions to capture cross-task fine-grained ranking information, which could avoid task conflicts by preserving the cross-task consistent knowledge; 2) Knowledge Distillation: We design a knowledge distillation approach based on augmented tasks for sharing ranking knowledge, where tasks' predictions are aligned with a calibration process; 3) Model Training: Teacher and student models are trained in an end-to-end manner, with a novel error correction mechanism to speed up model training and improve knowledge quality. Comprehensive experiments on a public dataset and our production dataset are carried out to verify the effectiveness of TKD as well as the necessity of its key components.

poster session 5 @ blue 5, poster session 9 @ blue 5, poster session 5, poster session 9

Central to active learning (AL) is what data should be selected for annotation. Existing works attempt to select highly uncertain or informative data for annotation. Nevertheless, it remains unclear how selected data impacts the test performance of the task model used in AL. In this work, we explore such an impact by theoretically proving that selecting unlabeled data of higher gradient norm leads to a lower upper-bound of test loss, resulting in a better test performance. However, due to the lack of label information, directly computing gradient norm for unlabeled data is infeasible. To address this challenge, we propose two schemes, namely expected-gradnorm and entropy-gradnorm. The former computes the gradient norm by constructing an expected empirical loss while the latter constructs an unsupervised loss with entropy. Furthermore, we integrate the two schemes in a universal AL framework. We evaluate our method on classical image classification and semantic segmentation tasks. To demonstrate its competency in domain applications and its robustness to noise, we also validate our method on a cellular imaging analysis task, namely cryo-Electron Tomography subtomogram classification. Results demonstrate that our method achieves superior performance against the state of the art. Our source code is available at https://github.com/xulabs/aitom/tree/master/aitom/ml/active_learning/al_gradnorm.

poster session 2 @ blue 2, poster session 9 @ blue 2, poster session 2, poster session 9

Influence blocking maximization (IBM) is crucial in many critical real-world problems such as rumors prevention and epidemic containment. The existing work suffers from: (1) concentrating on uniform costs at the individual level, (2) mostly utilizing greedy approaches to approximate optimization, (3) lacking a proper graph representation for influence estimates. To address these issues, this research introduces a neural network model dubbed Neural Influence Blocking (\algo) for improved approximation and enhanced influence blocking effectiveness. The code is available at https://github.com/oates9895/NIB.

poster session 5 @ blue 5, poster session 9 @ blue 5, poster session 5, poster session 9

In black-box optimization problems, we aim to maximize an unknown objective function, where the function is only accessible through feedbacks of an evaluation or simulation oracle. In real-life, the feedbacks of such oracles are often noisy and available after some unknown delay that may depend on the computation time of the oracle. Additionally, if the exact evaluations are expensive but coarse approximations are available at a lower cost, the feedbacks can have multi-fidelity. In order to address this problem, we propose a generic extension of hierarchical optimistic tree search (HOO), called ProCrastinated Tree Search (PCTS), that flexibly accommodates a delay and noise-tolerant bandit algorithm. We provide a generic proof technique to quantify regret of PCTS under delayed, noisy, and multi-fidelity feedbacks. Specifically, we derive regret bounds of PCTS enabled with delayed-UCB1 (DUCB1) and delayed-UCB-V (DUCBV) algorithms. Given a horizon T, PCTS retains the regret bound of non-delayed HOO for expected delay of O(log T), and worsens by T^{(1-\alpha)/(d+2)} for expected delays of O(T^{1-\alpha}) for \alpha \in (0,1]. We experimentally validate on multiple synthetic functions and hyperparameter tuning problems that PCTS outperforms the state-of-the-art black-box optimization methods for feedbacks with different noise levels, delays, and fidelity.

poster session 4 @ blue 3, poster session 9 @ blue 3, poster session 4, poster session 9

The predict+optimize problem combines machine learning and combinatorial optimization by predicting the problem coefficients first and then using these coefficients to solve the optimization problem. While this problem can be solved in two separate stages, recent research shows end to end models can achieve better results. This requires differentiating through a discrete combinatorial function. Models that use differentiable surrogates are prone to approximation errors, while existing exact models are limited to dynamic programming, or they do not generalize well with scarce data. In this work we propose a novel divide and conquer algorithm based on transition points to reason over exact optimization problems and predict the coefficients using the optimization loss. Moreover, our model is not limited to dynamic programming problems. We also introduce a greedy version, which achieves similar results with less computation. In comparison with other predict+optimize frameworks, we show our method outperforms existing exact frameworks and can reason over hard combinatorial problems better than surrogate methods.

poster session 2 @ blue 4, poster session 9 @ blue 4, poster session 2, poster session 9

Reasoning is a dynamic process. In cognitive theories, the dynamics of reasoning refers to reasoning states over time after successive state transitions. Modeling the cognitive dynamics from the AI perspective is of utmost importance to simulate human reasoning capability. In this paper, we propose to learn the reasoning dynamics of visual relational reasoning by casting it as a path routing task. We present a reinforced path routing method that represents an input image via a structured visual graph and introduces a reinforcement learning based model to explore paths (sequences of nodes) over the graph based on an input sentence to infer reasoning results. By exploring such paths, the proposed method clearly represents reasoning states and explicitly characterizes state transitions to fully model the reasoning dynamics for accurate and transparent visual relational reasoning. Extensive experiments on referring expression comprehension and visual question answering demonstrate the effectiveness of our method.

poster session 2 @ red 4, poster session 9 @ red 4, poster session 2, poster session 9

Infographics deal with representing data or information visually in a perceptually compelling manner. Recently, infographics have gained widespread popularity, giving rise to automated infographics synthesis from texts. Our research follows an ontological approach to automatically extract the necessary indicators from an input sentence and synthesize an infographic corresponding to it. This work includes (1) the creation of a dataset, (2) an end-to-end domain-agnostic framework, and (3) demonstrating the application of the proposed framework. The results demonstrate our framework's ability to extract the necessary textual cues from real-world textual descriptions (from various domains) and synthesize meaningful infographics.

poster session 6 @ red 5, poster session 9 @ red 5, poster session 6, poster session 9

Bounding box regression is an important component in object detection. Recent work achieves promising performance by optimizing the Intersection over Union~(IoU). However, IoU-based loss has the gradient vanish problem in the case of low overlapping bounding boxes, and the model could easily ignore these simple cases. In this paper, we propose Side Overlap (SO) loss by maximizing the side overlap of two bounding boxes, which puts more penalty for low overlapping bounding box cases. Besides, to speed up the convergence, the Corner Distance (CD) is added into the objective function. Combining the Side Overlap and Corner Distance, we get a new regression objective function, Side and Corner Align Loss (SCALoss). The SCALoss is well-correlated with IoU loss, which also benefits the evaluation metric but produces more penalty for low-overlapping cases. It can serve as a comprehensive similarity measure, leading to better localization performance and faster convergence speed. Experiments on COCO, PASCAL VOC, and LVIS benchmarks show that SCALoss can bring consistent improvement and outperform $\ell_n$ loss and IoU based loss with popular object detectors such as YOLOV3, SSD, Reppoints, Faster-RCNN.

poster session 2 @ red 3, poster session 9 @ red 3, poster session 2, poster session 9

Generalizing the medical image segmentation algorithms to unseen domains is an important research topic for computer- aided diagnosis and surgery. Most existing methods require a fully labeled dataset in each source domain. Although (Liu et al. 2021b) developed a semi-supervised domain general- ized method, it still requires the domain labels. This paper presents a novel confidence-aware cross pseudo supervision algorithm for semi-supervised domain generalized medical image segmentation. The main goal is to enhance the pseudo label quality for unlabeled images from unknown distribu- tions. To achieve it, we perform the Fourier transformation to learn low-level statistic information across domains and augment the images to incorporate cross-domain information. With these augmentations as perturbations, we feed the input to a confidence-aware cross pseudo supervision network to measure the variance of pseudo labels and regularize the network to learn with more confident pseudo labels. Our method sets new records on public datasets, i.e., M&Ms and SCGM. Notably, without using domain labels, our method surpasses the prior art that even uses domain labels by 11.67% on Dice on M&Ms dataset with 2% labeled data.Code is available at https://github.com/XMed-Lab/EPL SemiDG.

poster session 2 @ red 2, poster session 9 @ red 2, poster session 2, poster session 9

Graph Neural Networks (GNNs) have shown promising results on a broad spectrum of applications. Most empirical studies of GNNs directly take the observed graph as input, assuming the observed structure perfectly depicts the accurate and complete relations between nodes. However, graphs in the real-world are inevitably noisy or incomplete, which could even exacerbate the quality of graph representations. In this work, we propose a novel Variational Information Bottleneck guided Graph Structure Learning framework, namely VIB-GSL, in the perspective of information theory. VIB-GSL is the first attempt to advance the Information Bottleneck (IB) principle for graph structure learning, providing a more elegant and universal framework for mining underlying task-relevant relations. VIB-GSL learns an informative and compressive graph structure to distill the actionable information for specific downstream tasks. VIB-GSL deduces a variational approximation for irregular graph data to form a tractable IB objective function, which facilitates training stability. Extensive experimental results demonstrate that the superior effectiveness and robustness of the proposed VIB-GSL against other strong baselines.

poster session 5 @ blue 5, poster session 9 @ blue 5, oral session 9 @ blue 5, poster session 5, poster session 9, oral session 9

We introduce novel methods for encoding acyclicity and s-t-reachability constraints for propositional formulas with underlying directed graphs. They are based on \emph{vertex elimination graphs}, which makes them suitable for cases where the underlying graph has a low \emph{directed elimination width}. In contrast to solvers with ad hoc constraint propagators for acyclicity and reachability constraints such as GraphSAT, our methods encode these constraints as standard propositional clauses, making them directly applicable with any SAT solver. An empirical study demonstrates that our methods together with an efficient SAT solver do often outperform both earlier encodings of these constraints as well as GraphSAT, particularly when underlying graphs have low directed elimination width.

poster session 2 @ blue 4, poster session 9 @ blue 4, poster session 2, poster session 9

Near-term quantum hardware can support two-qubit operations only on the qubits that can interact with each other. Therefore, to execute an arbitrary quantum circuit on the hardware, compilers have to first perform the task of qubit routing, i.e., to transform the quantum circuit either by inserting additional SWAP gates or by reversing existing CNOT gates to satisfy the connectivity constraints of the target topology. The depth of the transformed quantum circuits is minimized by utilizing the Monte Carlo tree search (MCTS) to perform qubit routing by making it both construct each action and search over the space of all actions. It is aided in performing these tasks by a Graph neural network that evaluates the value function and action probabilities for each state. Along with this, we propose a new method of adding mutex-lock like variables in our state representation which helps factor in the parallelization of the scheduled operations, thereby pruning the depth of the output circuit. Overall, our procedure (referred to as QRoute) performs qubit routing in a hardware agnostic manner, and it outperforms other available qubit routing implementations on various circuit benchmarks.

poster session 2 @ blue 1, poster session 9 @ blue 1, poster session 2, poster session 9

Astronomical interferometry enables a collection of telescopes to achieve angular resolutions comparable to that of a single, much larger telescope. This is achieved by combining simultaneous observations from pairs of telescopes such that the signal is mathematically equivalent to sampling the Fourier domain of the object. However, reconstructing images from such sparse sampling is a challenging and ill-posed problem, with current methods requiring precise tuning of parameters and manual, iterative cleaning by experts. We present a novel deep learning approach in which the representation in the Fourier domain of an astronomical source is learned implicitly using a neural field representation. Data-driven priors can be added through a transformer encoder. Results on synthetically observed galaxies show that transformer-conditioned neural fields can successfully reconstruct astronomical observations even when the number of visibilities is very sparse.

poster session 2 @ blue 1, poster session 9 @ blue 1, poster session 2, poster session 9

Modern recommender systems are required to adapt to the change in popularity of items and user preferences. Such problem is known as the temporal dynamics problem, and it is one of the main challenges in recommender system modeling. Different from the popular recurrent modeling approach, we propose a new solution named LeapRec to the temporal dynamic problem by using trajectory-based meta-learning to model time dependencies. LeapRec characterizes temporal dynamics by two complement components named global time leap (GTL) and ordered time leap (OTL). By design, GTL learns long-term patterns by finding the shortest learning path across unordered temporal data. Cooperatively, OTL learns short-term patterns by considering the sequential nature of the temporal data. Our experimental results show that LeapRec consistently outperforms the state-of-the-art methods on several datasets and recommendation metrics. Furthermore, we provide an empirical study of the interaction between GTL and OTL, showing the effects of long- and short-term modeling.

poster session 5 @ blue 5, poster session 9 @ blue 5, poster session 5, poster session 9

Psychological concepts can help computational linguists to better model the latent semantic spaces of emotions, and understand the underlying states motivating the sharing or suppressing of emotions. This abstract applies the understanding of agency and social interaction in the happiness semantic space to its role in positive emotion. First, BERT-based fine-tuning yields an expanded seed set to understand the vocabulary of the latent space. Next, results benchmarked against many emotion datasets suggest that the approach is valid, robust, offers an improvement over direct prediction, and is useful for downstream predictive tasks related to psychological states.

poster session 6 @ red 5, poster session 9 @ red 5, poster session 6, poster session 9

Machine learning methods such as deep neural networks (DNNs), despite their success across different domains, are known to often generate incorrect predictions with high confi- dence on inputs outside their training distribution. The deploy- ment of DNNs in safety-critical domains requires detection of out-of-distribution (OOD) data so that DNNs can abstain from making predictions on those. A number of methods have been recently developed for OOD detection, but there is still room for improvement. We propose the new method iDECODe, leveraging in-distribution equivariance for conformal OOD detection. It relies on a novel base non-conformity measure and a new aggregation method, used in the inductive confor- mal anomaly detection framework, thereby guaranteeing a bounded false detection rate. We demonstrate the efficacy of iDECODe by experiments on image and audio datasets, obtain- ing state-of-the-art results. We also show that iDECODe can detect adversarial examples. Code, pre-trained models, and data are available at https://github.com/ramneetk/iDECODe.

poster session 5 @ blue 5, poster session 9 @ blue 5, poster session 5, poster session 9

We aim to explain a black-box classifier with the form: `data X is classified as class Y because X \textit{has} A, B and \textit{does not have} C' in which A, B, and C are high-level concepts. The challenge is that we have to discover in an unsupervised manner a set of concepts, i.e., A, B and C, that is useful for explaining the classifier. We first introduce a structural generative model that is suitable to express and discover such concepts. We then propose a learning process that simultaneously learns the data distribution and encourages certain concepts to have a large causal influence on the classifier output. Our method also allows easy integration of user's prior knowledge to induce high interpretability of concepts. Finally, using multiple datasets, we demonstrate that the proposed method can discover useful concepts for explanation in this form.

poster session 2 @ blue 1, poster session 9 @ blue 1, poster session 2, poster session 9

Predicting the diffusion cascades is a critical task to understand information spread on social networks. Previous methods usually focus on the order or structure of the infected users in a single cascade, thus ignoring the global dependencies of users and cascades, limiting the performance of prediction. Current strategies to introduce social networks only learn the social homogeneity among users, which is not enough to describe their interaction preferences, let alone the dynamic changes. To address the above issues, we propose a novel information diffusion prediction model named Memory-enhanced Sequential Hypergraph Attention Networks (MS-HGAT). Specifically, to introduce the global dependencies of users, we not only take advantages of their friendships, but also consider their interactions at the cascade level. Furthermore, to dynamically capture user' preferences, we divide the diffusion hypergraph into several sub graphs based on timestamps, develop Hypergraph Attention Networks to learn the sequential hypergraphs, and connect them with gated fusion strategy. In addition, a memory-enhanced embedding lookup module is proposed to capture the learned user representations into the cascade-specific embedding space, thus highlighting the feature interaction within the cascade. The experimental results over four realistic datasets demonstrate that MS-HGAT significantly outperforms the state-of-the-art diffusion prediction models in both Hits@K and MAP@k metrics.

poster session 5 @ blue 5, poster session 9 @ blue 5, poster session 5, poster session 9

Optimization of real-world black-box functions defined over purely categorical variables is an active area of research. In particular, optimization and design of biological sequences with specific functional or structural properties have a profound impact in medicine, materials science, and biotechnology. Standalone search algorithms, such as simulated annealing (SA) and Monte Carlo tree search (MCTS), are typically used for such optimization problems. In order to improve the performance and sample efficiency of such algorithms, we propose to use existing methods in conjunction with a surrogate model for the black-box evaluations over purely categorical variables. To this end, we present two different representations, a group-theoretic Fourier expansion and an abridged one-hot encoded Boolean Fourier expansion. To learn such representations, we consider two different settings to update our surrogate model. First, we utilize an adversarial online regression setting where Fourier characters of each representation are considered as experts and their respective coefficients are updated via an exponential weight update rule each time the black box is evaluated. Second, we consider a Bayesian setting where queries are selected via Thompson sampling and the posterior is updated via a sparse Bayesian regression model (over our proposed representation) with a regularized horseshoe prior. Numerical experiments over synthetic benchmarks as well as real-world RNA sequence optimization and design problems demonstrate the representational power of the proposed methods, which achieve competitive or superior performance compared to state-of-the-art counterparts, while improving the computation cost and/or sample efficiency, substantially.

poster session 2 @ blue 2, poster session 9 @ blue 2, poster session 2, poster session 9

In this article, we proposed a technique for action localization and recognition from long untrimmed videos. It consists of C3D CNN model followed by the action mining using the localization model, where the KNN classifier is used. We segment the video into expressible sub-action known as action-bytes. The pseudo labels have been used to train the localization model, which makes the trimmed videos untrimmed for action-bytes. We present experimental results on the recent benchmark trimmed video dataset “Thumos14”.

poster session 5 @ red 1, poster session 9 @ red 1, poster session 5, poster session 9

In a convolutional object detector, the detection accuracy can be degraded often due to the low feature discriminability caused by geometric variation or transformation of an object. In this paper, we propose a deformable part region learning in order to allow decomposed part regions to be deformable according to geometric transformation of an object. To this end, we introduce trainable geometric parameters for the location of each part model. Because the ground truth of the part models is not available, we design classification and mask losses for part models, and learn the geometric parameters by minimizing an integral loss including those part losses. As a result, we can train a deformable part region network without extra super-vision and make each part model deformable according to object scale variation. Furthermore, for improving cascade object detection and instance segmentation, we present a Cascade deformable part region architecture which can refine whole and part detections iteratively in the cascade manner. Without bells and whistles, our implementation of a Cascade deformable part region detector achieves better detection and segmentation mAPs on COCO and VOC datasets, compared to the recent cascade and other state-of-the-art detectors.

poster session 2 @ red 3, poster session 9 @ red 3, poster session 2, poster session 9

Automatic identification of salient aspects from user reviews is especially useful for opinion analysis. There has been significant progress in utilizing weakly supervised approaches, which require only a small set of seed words for training aspect classifiers. However, there is still room for improvement, as these methods do not employ hyperbolic space information, nor do they account for the different latent semantics of individual seed words. We propose HDAE, a hyperbolic disentangled aspect extractor which includes a hyperbolic aspect classifier to infer review segments' aspects, and an aspect-disentangled representation to model the latent semantics of each seed word. Superior performance on two datasets and the embedding visualization demonstrate that \system is a more effective approach to leveraging seed words. We further show the effectiveness of the proposed components by an ablation study and a case study.

poster session 6 @ red 5, poster session 9 @ red 5, poster session 6, poster session 9

As a key component of talking face generation, lip movements generation determines the naturalness and coherence of the generated talking face video. Prior literature mainly focuses on speech-to-lip generation while there is a paucity in text-to-lip (T2L) generation. T2L is a challenging task and existing end-to-end works depend on the attention mechanism and autoregressive (AR) decoding manner. However, the AR decoding manner generates current lip frame conditioned on frames generated previously, which inherently hinders the inference speed, and also has a detrimental effect on the quality of generated lip frames due to error propagation. This encourages the research of parallel T2L generation. In this work, we propose a novel parallel decoding model for fast and high-fidelity text-to-lip generation (ParaLip). Specifically, we predict the duration of the encoded linguistic features and model the target lip frames conditioned on the encoded linguistic features with their duration in a non-autoregressive manner. Furthermore, we incorporate the structural similarity index loss and adversarial learning to improve perceptual quality of generated lip frames and alleviate the blurry prediction problem. Extensive experiments conducted on GRID and TCD-TIMIT datasets demonstrate the superiority of proposed methods. Video samples are available via \url{https://paralip.github.io/}.

poster session 2 @ red 4, poster session 9 @ red 4, poster session 2, poster session 9

Learning linear temporal logic on finite traces (LTLf ) formulae aims to learn a target formula that characterizes the highlevel behavior of a system from observation traces in planning. Existing approaches to learning LTLf formulae, however, can hardly learn accurate LTLf formulae from noisy data. It is challenging to design an efficient search mechanism in the large search space in form of arbitrary LTLf formulae while alleviating the wrong search bias resulting from noisy data. In this paper, we tackle this problem by bridging LTLf inference to GNN inference. Our key theoretical contribution is showing that GNN inference can simulate LTLf inference to distinguish traces. Based on our theoretical result, we design a GNN-based approach, GLTLf, which combines GNN inference and parameter interpretation to seek the target formula in the large search space. Thanks to the non-deterministic learning process of GNNs, GLTLf is able to cope with noise. We evaluate GLTLf on various datasets with noise. Our experimental results confirm the effectiveness of GNN inference in learning LTLf formulae and show that GLTLf is superior to the state-of-the-art approaches.

poster session 2 @ blue 1, poster session 9 @ blue 1, poster session 2, poster session 9

The one-shot multi-object tracking, which integrates object detection and ID embedding extraction into a unified network, has achieved groundbreaking results in recent years. However, current one-shot trackers solely rely on single-frame detections to predict candidate bounding boxes, which may be unreliable when facing disastrous visual degradation, e.g., motion blur, occlusions. Once a target bounding box is mistakenly classified as background by the detector, the temporal consistency of its corresponding tracklet will be no longer maintained. In this paper, we set out to restore the bounding boxes misclassified as ``fake background'' by proposing a re-check network. The re-check network innovatively expands the role of ID embedding from data association to motion forecasting by effectively propagating previous tracklets to the current frame with a small overhead. Note that the propagation results are yielded by an independent and efficient embedding search, preventing the model from over-relying on detection results. Eventually, it helps to reload the ``fake background'' and repair the broken tracklets. Building on a strong baseline CSTrack, we construct a new one-shot tracker and achieve favorable gains by 70.7 ➡ 76.4, 70.6 ➡ 76.3 MOTA on MOT16 and MOT17, respectively. It also reaches a new state-of-the-art MOTA and IDF1 performance. Code is released at https://github.com/JudasDie/SOTS.

poster session 5 @ red 1, poster session 9 @ red 1, poster session 5, poster session 9

Combinatorial optimization problems are ubiquitous for decision making in planning social infrastructures. In real-world scenarios, a decision-maker needs to solve his/her problem iteratively until he/she satisfies solutions, but such an iterative process remains challenging. This paper studies a new explainable framework, particularly for finding meeting points, which is a key optimization problem for designing facility locations. Our framework automatically fills the gap between its input instance and instances from which a user could obtain the desired outcome, where computed solutions are judged by the user. The framework also provides users with explanations, representing the difference of instances for deeply understanding the process and its inside. Explanations are clues for users to understand their situation and implement suggested results in practice (e.g., designing a coupon for free travel). We experimentally demonstrate that our search-based framework is promising to solve instances with generating explanations in a sequential decision-making process.

poster session 2 @ blue 4, poster session 9 @ blue 4, oral session 2 @ blue 4, poster session 2, poster session 9, oral session 2

Deep Neural Networks (DNNs) generally require large-scale datasets for training. Since manually obtaining clean labels for large datasets is extremely expensive, unsupervised models based on domain-specific heuristics can be used to efficiently infer the labels for such datasets. However, the labels from such inferred sources are typically noisy, which could easily mislead and lessen the generalizability of DNNs. Most approaches proposed in the literature to address this problem assume the label noise depends only on the true class of an instance (i.e., class-conditional noise). However, this assumption is not realistic for the inferred labels as they are typically inferred based on the features of the instances. The few recent attempts to model such instance-dependent (i.e., feature-dependent) noise require auxiliary information about the label noise (e.g., noise rates or clean samples). This work proposes a theoretically motivated framework to correct label noise in the presence of multiple labels inferred from unsupervised models. The framework consists of two modules: (1) MULTI-IDNC, a novel approach to correct label noise that is instance-dependent yet not class-conditional; (2) MULTI-CCNC, which extends an existing class-conditional noise-robust approach to yield improved class-conditional noise correction using multiple noisy label sources. We conduct experiments using nine real-world datasets for three different classification tasks (images, text and graph nodes). Our results show that our approach achieves notable improvements (e.g., 6.4% in accuracy) against state-of-the-art baselines while dealing with both instance-dependent and class-conditional noise in inferred label sources.

poster session 2 @ blue 1, poster session 9 @ blue 1, poster session 2, poster session 9

Inharmonious region localization aims to localize the region in a synthetic image which is incompatible with surrounding background. The inharmony issue is mainly attributed to the color and illumination inconsistency produced by image editing techniques. In this work, we tend to transform the input image to another color space to magnify the domain discrepancy between inharmonious region and background, so that the model can identify the inharmonious region more easily. To this end, we present a novel framework consisting of a color mapping module and an inharmonious region localization network, in which the former is equipped with a novel domain discrepancy magnification loss and the latter could be an arbitrary localization network. Extensive experiments on image harmonization dataset show the superiority of our designed framework. Our code is available at \url{https://github.com/bcmi/MadisNet-Inharmonious-Region-Localization}.

poster session 2 @ red 4, poster session 9 @ red 4, oral session 9 @ red 4, poster session 2, poster session 9, oral session 9

Tree ensembles (TEs) denote a prevalent machine learning model that do not offer guarantees of interpretability, that represent a challenge from the perspective of explainable artificial intelligence. Besides model agnostic approaches, recent work proposed to explain TEs with formally-defined explanations, which are computed with oracles for propositional satisfiability (SAT) and satisfiability modulo theories. The computation of explanations for TEs involves linear constraints to express the prediction. In practice, this deteriorates scalability of the underlying reasoners. Motivated by the inherent propositional nature of TEs, this paper proposes to circumvent the need for linear constraints and instead employ an optimization engine for pure propositional logic to efficiently handle the prediction. Concretely, the paper proposes to use a MaxSAT solver and exploit the objective function to determine a winning class. This is achieved by devising a propositional encoding for computing explanations of TEs. Furthermore, the paper proposes additional heuristics to improve the underlying MaxSAT solving procedure. Experimental results obtained on a wide range of publicly available datasets demonstrate that the proposed MaxSAT-based approach is either on par or outperforms the existing reasoning-based explainers, thus representing a robust and efficient alternative for computing formal explanations for TEs.

poster session 2 @ blue 4, poster session 9 @ blue 4, oral session 9 @ blue 4, poster session 2, poster session 9, oral session 9

We proposed a Prior Gradient Mask Guided Pruning-aware Fine-tuning (PGMPF) framework to accelerate deep Convolutional Neural Networks (CNNs). In detail, the proposed PGMPF selectively suppresses the gradient of those ”unimportant” parameters via a prior gradient mask generated by the pruning criterion during fine-tuning. PGMPF has three charming characteristics over previous works: (1) Pruning-aware network fine-tuning. A typical pruning pipeline consists of training, pruning and fine-tuning, which are relatively independent, while PGMPF utilizes a variant of the pruning mask as a prior gradient mask to guide fine-tuning, without complicated pruning criteria. (2) An excellent tradeoff between large model capacity during fine-tuning and stable convergence speed to obtain the final compact model. Previous works preserve more training information of pruned parameters during fine-tuning to pursue better performance, which would incur catastrophic non-convergence of the pruned model for relatively large pruning rates, while our PGMPF greatly stabilizes the fine-tuning phase by gradually constraining the learning rate of those ”unimportant” parameters. (3) Channel-wise random dropout of the prior gradient mask to impose some gradient noise to fine-tuning to further improve the robustness of final compact model. Experimental results on three image classification benchmarks CIFAR10/ 100 and ILSVRC-2012 demonstrate the effectiveness of our method for various CNN architectures, datasets and pruning rates. Notably, on ILSVRC-2012, PGMPF reduces 53.5% FLOPs on ResNet-50 with only 0.90% top-1 accuracy drop and 0.52% top-5 accuracy drop, which has advanced the state-of-the-art with negligible extra computational cost.

poster session 2 @ red 3, poster session 9 @ red 3, poster session 2, poster session 9

The k-undercover Boolean Matrix Factorization problem aims at approximating an (m×n) Boolean matrix X as the Boolean product of an (m×k) and a (k×n) matrices A ◦ B such that X is a cover of A ◦ B, i.e., no representation error is allowed on the 0’s entries of the matrix X. In this paper, we propose two exact methods based on MaxSAT encodings to infer optimal and “block-optimal” k-undercover. From a theoretical standpoint, we prove that our method of inferring “block-optimal” k-undercover is a (1−1/e)-approximation for the optimal k-undercover problem, and from a practical standpoint, experimental results show that our “block-optimal” k-undercover algorithm outperforms the state of the art even when compared with algorithms for the more general k-undercover Boolean Matrix Factorization problem for which only minimizing reconstruction error is required.

poster session 2 @ blue 4, poster session 9 @ blue 4, oral session 9 @ blue 4, poster session 2, poster session 9, oral session 9

Recently, Transformers have shown promising performance in various vision tasks. To reduce the quadratic computation complexity caused by the global self-attention, various methods constrain the range of attention within a local region to improve its efficiency. Consequently, their receptive fields in a single attention layer are not large enough, resulting in insufficient context modeling. To address this issue, we propose a Pale-Shaped self-Attention (PS-Attention), which performs self-attention within a pale-shaped region. Compared to the global self-attention, PS-Attention can reduce the computation and memory costs significantly. Meanwhile, it can capture richer contextual information under the similar computation complexity with previous local self-attention mechanisms. Based on the PS-Attention, we develop a general Vision Transformer backbone with a hierarchical architecture, named Pale Transformer, which achieves 83.4%, 84.3%, and 84.9% Top-1 accuracy with the model size of 22M, 48M, and 85M respectively for 224×224 ImageNet-1K classification, outperforming the previous Vision Transformer backbones. For downstream tasks, our Pale Transformer backbone performs better than the recent state-of-the-art CSWin Transformer by a large margin on ADE20K semantic segmentation and COCO object detection & instance segmentation. The code will be released on \url{https://github.com/BR-IDL/PaddleViT}.

poster session 2 @ red 3, poster session 9 @ red 3, oral session 2 @ red 3, poster session 2, poster session 9, oral session 2

Improving health equity is an urgent task for our society. The advent of mobile clinics plays an important role in enhancing health equity, as they can provide easier access to preventive healthcare for patients from disadvantaged populations. For effective functioning of mobile clinics, accurate prediction of demand (expected number of individuals visiting mobile clinic) is the key to their daily operations and staff/resource allocation. Despite its importance, there have been very limited studies on predicting demand of mobile clinics. To the best of our knowledge, we are among the first to explore this area, using AI-based techniques. A crucial challenge in this task is that there are no known existing data sources from which we can extract useful information to account for the exogenous factors that may affect the demand, while considering protection of client privacy. We propose a novel methodology that completely uses public data sources to extract the features, with several new components that are designed to improve the prediction. Empirical evaluation on a real-world dataset from the mobile clinic The Family Van shows that, by leveraging publicly available data (which introduces no extra monetary cost to the mobile clinics), our AI-based method achieves 26.4% - 51.8% lower Root Mean Squared Error (RMSE) than the historical average-based estimation (which is presently employed by mobile clinics like The Family Van). Our algorithm makes it possible for mobile clinics to plan proactively, rather than reactively, as what has been doing.

poster session 4 @ red 6, poster session 9 @ red 6, poster session 4, poster session 9