AAAI 2022 Papers

Recently, many approaches tackle the Unsupervised Domain Adaptive person re-identification (UDA re-ID) problem through pseudo-label-based contrastive learning. During training, a uni-centroid representation is obtained by simply averaging all the instance features from a cluster with the same pseudo label. However, a cluster may contain images with different identities (label noises) due to the imperfect clustering results, which makes the uni-centroid representation inappropriate. In this paper, we present a novel Multi-Centroid Memory (MCM) to adaptively capture different identity information within the cluster. MCM can effectively alleviate the issue of label noises by selecting proper positive/negative centroids for the query image. Moreover, we further propose two strategies to improve the contrastive learning process. First, we present a Domain-Specific Contrastive Learning (DSCL) mechanism to fully explore intra-domain information by comparing samples only from the same domain. Second, we propose Second-Order Nearest Interpolation (SONI) to obtain abundant and informative negative samples. We integrate MCM, DSCL, and SONI into a unified framework named Multi-Centroid Representation Network (MCRN). Extensive experiments demonstrate the superiority of MCRN over state-of-the-art approaches on multiple UDA re-ID tasks and fully unsupervised re-ID tasks.

We posit a new mechanism for cooperation in multi-agent reinforcement learning (MARL) based upon any nonlinear function of the team's long-term state-action occupancy measure, i.e., a general utility. This subsumes the cumulative return but also allows one to incorporate risk-sensitivity, exploration, and priors. We derive the Decentralized Shadow Reward Actor-Critic (DSAC) in which agents alternate between policy evaluation (critic), weighted averaging with neighbors (information mixing), and local gradient updates for their policy parameters (actor). DSAC augments the classic critic step by requiring agents to (i) estimate their local occupancy measure in order to (ii) estimate the derivative of the local utility with respect to their occupancy measure, i.e., the ``shadow reward". DSAC converges to ϵ-stationarity in O(1/ϵ^2.5) or faster O(1/ϵ^2) steps with high probability, depending on the amount of communications. We further establish the non-existence of spurious stationary points for this problem, that is, DSAC finds the globally optimal policy. Experiments demonstrate the merits of goals beyond the cumulative return in cooperative MARL.

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.

Recently, there has been an increasing interest in building question answering (QA) models that reason across multiple modalities, such as text and images. However, QA using images is often limited to just picking the answer from a pre-defined set of options. In addition, images in the real world, especially in news, have objects that are co-referential to the text, with complementary information from both modalities. In this paper, we present a new QA evaluation benchmark with 1,384 questions over news articles that require cross-media grounding of objects in images onto text. Specifically, the task involves multi-hop questions that require reasoning over image-caption pairs to identify the grounded visual object being referred to and then predicting a span from the news body text to answer the question. In addition, we introduce a novel multimedia data augmentation framework, based on cross-media knowledge extraction and synthetic question-answer generation, to automatically augment data that can provide weak supervision for this task. We evaluate both pipeline-based and end-to-end pretraining-based multimedia QA models on our benchmark, and show that they achieve promising performance, while considerably lagging behind human performance hence leaving large room for future work on this challenging new task.

Multimodal sensors (visual, non-visual, and wearable) can provide complementary information to develop robust perception systems for recognizing activities accurately. However, it is challenging to extract robust multimodal representations due to the heterogeneous characteristics of data from multimodal sensors and disparate human activities, especially in the presence of noisy and misaligned sensor data. In this work, we propose a cooperative multitask learning-based guided multimodal fusion approach, MuMu, to extract robust multimodal representations for human activity recognition (HAR). MuMu employs an auxiliary task learning approach to extract features specific to each set of activities with shared characteristics (activity-group). MuMu then utilizes activity-group-specific features to direct our proposed Guided Multimodal Fusion Approach (GM-Fusion) for extracting complementary multimodal representations, designed as the target task. We evaluated MuMu by comparing its performance to state-of-the-art multimodal HAR approaches on three activity datasets. Our extensive experimental results suggest that MuMu outperforms all the evaluated approaches across all three datasets. Additionally, the ablation study suggests that MuMu significantly outperforms the baseline models (p

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 characterization 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.

For a monocular camera-based navigation system, if we could effectively explore scene geometric cues from RGB images, the geometry information will significantly facilitate the efficiency of the navigation system. Motivated by this, we propose a highly efficient point-goal navigation framework, dubbed Geo-Nav. In a nutshell, our Geo-Nav consists of two parts: a visual perception part and a navigation part. In the visual perception part, we firstly propose a Self-supervised Depth Estimation network (SDE) specially tailored for the monocular camera-based navigation agent. Our SDE learns a mapping from an RGB input image to its corresponding depth image by exploring scene geometric constraints in a self-consistency manner. Then, in order to achieve a representative visual representation from the RGB inputs and learned depth images, we propose a Cross-modality Pyramid Fusion module (CPF). Concretely, our CPF computes a patch-wise cross-modality correlation between different modal features and exploits the correlation to fuse and enhance features at each scale. Thanks to the patch-wise nature of our CPF, we can fuse feature maps at high resolution, allowing our visual network to perceive more image details. In the navigation part, our extracted visual representations are fed to a navigation policy network to learn how to map the visual representations to agent actions effectively. Extensive experiments on a widely-used multiple-room environment Gibson demonstrate that Geo-Nav outperforms the state-of-the-art in terms of efficiency and effectiveness.

Molecular representation learning contributes to multiple downstream tasks such as molecular property prediction and drug design. To properly represent molecules, graph contrastive learning is a promising paradigm as it utilizes self-supervision signals and has no requirements for human annotations. However, prior works fail to incorporate fundamental domain knowledge into graph semantics and thus ignore the correlations between atoms that have common attributes but are not directly connected by bonds. To address these issues, we construct a Chemical Element Knowledge Graph (KG) to summarize microscopic associations between elements and propose a novel Knowledge-enhanced Contrastive Learning (KCL) framework for molecular representation learning. KCL framework consists of three modules. The first module, knowledge-guided graph augmentation, augments the original molecular graph based on the Chemical Element KG. The second module, knowledge-aware graph representation, extracts molecular representations with a common graph encoder for the original molecular graph and a Knowledge-aware Message Passing Neural Network (KMPNN) to encode complex information in the augmented molecular graph. The final module is a contrastive objective, where we maximize agreement between these two views of molecular graphs. Extensive experiments demonstrated that KCL obtained superior performances against state-of-the-art baselines on eight molecular datasets. Visualization experiments properly interpret what KCL has learned from atoms and attributes in the augmented molecular graphs.

Although considerable progress has been achieved regarding the transformers in recent years, the large number of parameters, quadratic computational complexity, and memory cost conditioned on long sequences make the transformers hard to train and implement, especially in edge computing configurations. In this case, a dizzying number of works have sought to make improvements around computational and memory efficiency upon the original transformer architecture. Nevertheless, many of them restrict the context in the attention to seek a trade-off between cost and performance with prior knowledge of orderly stored data. It is imperative to dig deep into an efficient feature extractor for point clouds due to their irregularity and a large number of points. In this paper, we propose a novel skeleton decomposition-based self-attention (SD-SA) which has no sequence length limit and exhibits favorable scalability in long-sequence models. Due to the numerical low-rank nature of self-attention, we approximate it by the skeleton decomposition method while maintaining its effectiveness. At this point, we have shown that the proposed method works for the proposed approach on point cloud classification, segmentation, and detection tasks on the ModelNet40, ShapeNet, and KITTI datasets, respectively. Our approach significantly improves the efficiency of the point cloud transformer and exceeds other efficient transformers on point cloud tasks in terms of the speed at comparable performance.

The classic Cluster Editing problem (also known as Correlation Clustering) asks to transform a given graph into a disjoint union of cliques (clusters) by a small number of edge modifications. When applied to vertex-colored graphs (the colors representing subgroups), standard algorithms for the NP-hard Cluster Editing problem may yield solutions that are biased towards subgroups of data (e.g., demographic groups), measured in the number of modifications incident to the members of the subgroups. We propose a modification fairness constraint which ensures that the number of edits incident to each subgroup is proportional to its size. To start with, we study Modification-Fair Cluster Editing for graphs with two vertex colors. We show that the problem is NP-hard even if one may only insert edges within a subgroup; note that in the classic "non-fair" setting, this case is trivially polynomial-time solvable. However, in the more general editing form, the modification-fair variant remains fixed-parameter tractable with respect to the number of edge edits. We complement these and further theoretical results with an empirical analysis of our model on real-world social networks where we find that the price of modification-fairness is surprisingly low, that is, the cost of optimal modification-fair differs from the cost of optimal "non-fair" solutions only by a small percentage.

Traditionally, when recommender systems are formalized as multi-armed bandits, the policy of the recommender system influences the rewards accrued, but not the length of interaction. However, in real-world systems, dissatisfied users may depart (and never come back). In this work, we propose a novel multi-armed bandit setup that captures such policy-dependent horizons. Our setup consists of a finite set of user types, and multiple arms with Bernoulli payoffs. Each (user type, arm) tuple corresponds to an (unknown) reward probability. Each user's type is initially unknown and can only be inferred through their response to recommendations. Moreover, if a user is dissatisfied with their recommendation, they might depart the system. We first address the case where all users share the same type, demonstrating that a recent UCB-based algorithm is optimal. We then move forward to the more challenging case, where users are divided among two types. While naive approaches cannot handle this setting, we provide an efficient learning algorithm that achieves O(sqrt(T)ln(T)) regret, where T is the number of users.

Digital cameras transform sensor RAW readings into RGB images by means of their Image Signal Processor (ISP). Computational photography tasks such as image denoising and colour constancy are commonly performed in the RAW domain, in part due to the inherent hardware design, but also due to the appealing simplicity of noise statistics that result from the direct sensor readings. Despite this, the availability of RAW images is limited in comparison with the abundance and diversity of available RGB data. Recent approaches have attempted to bridge this gap by estimating the RGB to RAW mapping: handcrafted model-based methods that are interpretable and controllable usually require manual parameter fine-tuning, while end-to-end learnable neural networks require large amounts of training data, at times with complex training procedures, and generally lack interpretability and parametric control. Towards addressing these existing limitations, we present a novel hybrid model-based and data-driven ISP that builds on canonical ISP operations and is both learnable and interpretable. Our proposed invertible model, capable of bidirectional mapping between RAW and RGB domains, employs end-to-end learning of rich parameter representations, i.e. dictionaries, that are free from direct parametric supervision and additionally enable simple and plausible data augmentation. We evidence the value of our data generation process by extensive experiments under both RAW image reconstruction and RAW image denoising tasks, obtaining state-of-the-art performance in both. Additionally, we show that our ISP can learn meaningful mappings from few data samples, and that denoising models trained with our dictionary-based data augmentation are competitive despite having only few or zero ground-truth labels.

Recently, Convolutional Neural Network (CNN) has achieved excellent performance in the classification task. It is widely known that CNN is deemed as a 'blackbox', which is hard for understanding the prediction mechanism and debugging the wrong prediction. Some model debugging and explanation works are developed for solving the above drawbacks. However, those methods focus on explanation and diagnosing possible causes for model prediction, based on which the researchers handle the following optimization of models manually. In this paper, we propose the first completely automatic model diagnosing and treating tool, termed as Model Doctor. Based on two discoveries that 1) each category is only correlated with sparse and specific convolution kernels, and 2) adversarial samples are isolated while normal samples are successive in the feature space, a simple aggregate gradient constraint is devised for effectively diagnosing and optimizing CNN classifiers. The aggregate gradient strategy is a versatile module for mainstream CNN classifiers. Extensive experiments demonstrate that the proposed Model Doctor applies to all existing CNN classifiers, and improves the accuracy of 16 mainstream CNN classifiers by 1%~5%.

RGB-infrared person re-identification is an emerging cross-modality re-identification task, which is very challenging due to significant modality discrepancy between RGB and infrared images. In this work, we propose a novel modality-adaptive mixup and invariant decomposition (MID) approach for RGB-infrared person re-identification towards learning modality-invariant and discriminative representations. MID designs a modality-adaptive mixup scheme to generate suitable mixed modality images between RGB and infrared images for mitigating the inherent modality discrepancy at the pixel-level. It formulates modality mixup procedure as Markov decision process, where an actor-critic agent learns dynamical and local linear interpolation policy between different regions of cross-modality images under a deep reinforcement learning framework. Such policy guarantees modality-invariance in a more continuous latent space and avoids manifold intrusion by the corrupted mixed modality samples. Moreover, to further counter modality discrepancy and enforce invariant visual semantics at the feature-level, MID employs modality-adaptive convolution decomposition to disassemble a regular convolution layer into modality-specific basis layers and a modality-shared coefficient layer. Extensive experimental results on two challenging benchmarks demonstrate superior performance of MID over state-of-the-art methods.

Advanced face swapping methods have achieved appealing results. However, most of these methods have many parameters and computations, which makes it challenging to apply them in real-time applications or deploy them on edge devices like mobile phones. In this work, we propose a lightweight Identity-aware Dynamic Network (IDN) for subject-agnostic face swapping by dynamically adjusting the model parameters according to the identity information. In particular, we design an efficient Identity Injection Module (IIM) by introducing two dynamic neural network techniques, including the weights prediction and weights modulation. Once the IDN is updated, it can be applied to swap faces given any target image or video. The presented IDN contains only 0.50M parameters and needs 0.33G FLOPs per frame, making it capable for real-time video face swapping on mobile phones. In addition, we introduce a knowledge distillation-based method for stable training, and a loss reweighting module is employed to obtain better synthesized results. Finally, our method achieves comparable results with the teacher models and other state-of-the-art methods.

We present a novel framework that brings the 3D motion retargeting task from controlled environments to in-the-wild scenarios. In particular, our method is capable of retargeting body motion from a character in a 2D monocular video to a 3D character without using any motion capture system or 3D reconstruction procedure. It is designed to leverage massive online videos for unsupervised training, needless of 3D annotations or motion-body pairing information. The proposed method is built upon two novel canonicalization operations, structure canonicalization and view canonicalization. Trained with the canonicalization operations and the derived regularizations, our method learns to factorize a skeleton sequence into three independent semantic subspaces, i.e., motion, structure, and view angle. The disentangled representation enables motion retargeting from 2D to 3D with high precision. Our method achieves superior performance on motion transfer benchmarks with large body variations and challenging actions. Notably, the canonicalized skeleton sequence could serve as a disentangled and interpretable representation of human motion that benefits action analysis and motion retrieval.

Acquiring high-quality temporal common sense (TCS) knowledge from free-form text is a crucial but challenging problem for event-centric natural language understanding, due to the language reporting bias problem: people rarely report the commonly observed events but highlight the special cases. For example, one may rarely report "I get up from bed in 1 minute", but we can observe "It takes me an hour to get up from bed every morning'' in text. Models directly trained upon such corpus would capture distorted TCS knowledge, which could influence the model performance. Prior work addresses this issue mainly by exploiting the interactions among temporal dimensions (e.g., duration, temporal relation between events) in a multi-task view. However, this line of work suffers the limitation of implicit, inadequate and unexplainable interactions modeling. In this paper, we propose a novel neural-logic based Soft Logic Enhanced Event Temporal Reasoning (SLEER) model for acquiring unbiased TCS knowledge, in which the complementary relationship among dimensions are explicitly represented as logic rules and modeled by t-norm fuzzy logics. SLEER can utilize logic rules to regularize its inference process. Experimental results on four intrinsic evaluation datasets and two extrinsic datasets show the efficiency of our proposed method.

Volitionality and subject animacy are fundamental and closely related properties of an event. Their classification is challenging because it requires contextual text understanding and a huge amount of labeled data. This paper proposes a novel method that jointly learns volitionality and subject animacy at a low cost, heuristically labeling events in a raw corpus. Volitionality labels are assigned using a small lexicon of volitional and non-volitional adverbs such as deliberately and accidentally; subject animacy labels are assigned using a list of animate and inanimate nouns obtained from ontological knowledge. We then consider the problem of learning a classifier from the labeled events so that it can perform well on unlabeled events without the words used for labeling. We view the problem as a bias reduction or unsupervised domain adaptation problem and apply the techniques. We conduct experiments with crowdsourced gold data in Japanese and English and show that our method effectively learns volitionality and subject animacy without manually labeled data.

Cross-Lingual Information Retrieval (CLIR) aims to rank the documents written in a language different from the user’s query. The intrinsic gap between different languages is an essential challenge for CLIR. In this paper, we introduce the multilingual knowledge graph (KG) to the CLIR task due to the sufficient information of entities in multiple languages. It is regarded as a “silver bullet” to simultaneously perform explicit alignment between queries and documents and also broaden the representations of queries. And we propose a model named CLIR with HIerarchical Knowledge Enhancement (HIKE) for our task. The proposed model encodes the textual information in queries, documents and the KG with multilingual BERT, and incorporates the KG information in the query-document matching process with a hierarchical information fusion mechanism. Particularly, HIKE first integrates the entities and their neighborhood in KG into query representations with a knowledge-level fusion, then combines the knowledge from both source and target languages to further mitigate the linguistic gap with a language-level fusion. Finally, experimental results demonstrate that HIKE achieves substantial improvements over state-of-the-art competitors.