AAAI 2023 论文列表

Offline multi-agent reinforcement learning (MARL) aims to learn effective multi-agent policies from pre-collected datasets, which is an important step toward the deployment of multi-agent systems in real-world applications. However, in practice, each individual behavior policy that generates multi-agent joint trajectories usually has a different level of how well it performs. e.g., an agent is a random policy while other agents are medium policies. In the cooperative game with global reward, one agent learned by existing offline MARL often inherits this random policy, jeopardizing the utility of the entire team. In this paper, we investigate offline MARL with explicit consideration on the diversity of agent-wise trajectories and propose a novel framework called Shared Individual Trajectories (SIT) to address this problem. Specifically, an attention-based reward decomposition network assigns the credit to each agent through a differentiable key-value memory mechanism in an offline manner. These decomposed credits are then used to reconstruct the joint offline datasets into prioritized experience replay with individual trajectories, thereafter agents can share their good trajectories and conservatively train their policies with a graph attention network (GAT) based critic. We evaluate our method in both discrete control (i.e., StarCraft II and multi-agent particle environment) and continuous control (i.e., multi-agent mujoco). The results indicate that our method achieves significantly better results in complex and mixed offline multi-agent datasets, especially when the difference of data quality between individual trajectories is large.

Mathematical reasoning is one of the crucial abilities of general artificial intelligence, which requires machines to master mathematical logic and knowledge from solving problems. However, existing approaches are not transparent (thus not interpretable) in terms of what knowledge has been learned and applied in the reasoning process. In this paper, we propose a general Learning by Applying (LeAp) framework to enhance existing models (backbones) in a principled way by explicit knowledge learning. In LeAp, we perform knowledge learning in a novel problem-knowledge-expression paradigm, with a Knowledge Encoder to acquire knowledge from problem data and a Knowledge Decoder to apply knowledge for expression reasoning. The learned mathematical knowledge, including word-word relations and word-operator relations, forms an explicit knowledge graph, which bridges the knowledge “learning” and “applying” organically. Moreover, for problem solving, we design a semantics-enhanced module and a reasoning-enhanced module that apply knowledge to improve the problem comprehension and symbol reasoning abilities of any backbone, respectively. We theoretically prove the superiority of LeAp's autonomous learning mechanism. Experiments on three real-world datasets show that LeAp improves all backbones' performances, learns accurate knowledge, and achieves a more interpretable reasoning process.

My research focuses on new techniques in machine learning and game theory to optimally allocate our scarce resources in multi-agent settings to maximize environmental sustainability. Drawing scientific questions from my close partnership with conservation organizations, I have advanced new lines of research in learning and planning under uncertainty, inspired by the low-data, noisy, and dynamic settings faced by rangers on the frontlines of protected areas.

Gaze estimator computes the gaze direction based on face images. Most existing gaze estimation methods perform well under within-dataset settings, but can not generalize to unseen domains. In particular, the ground-truth labels in unseen domain are often unavailable. In this paper, we propose a new domain generalization method based on gaze-consistent features. Our idea is to consider the gaze-irrelevant factors as unfavorable interference and disturb the training data against them, so that the model cannot fit to these gaze-irrelevant factors, instead, only fits to the gaze-consistent features. To this end, we first disturb the training data via adversarial attack or data augmentation based on the gaze-irrelevant factors, i.e., identity, expression, illumination and tone. Then we extract the gaze-consistent features by aligning the gaze features from disturbed data with non-disturbed gaze features. Experimental results show that our proposed method achieves state-of-the-art performance on gaze domain generalization task. Furthermore, our proposed method also improves domain adaption performance on gaze estimation. Our work provides new insight on gaze domain generalization task.

Recently, graph neural networks (GNNs) have been successfully applied to predicting molecular properties, which is one of the most classical cheminformatics tasks with various applications. Despite their effectiveness, we empirically observe that training a single GNN model for diverse molecules with distinct structural patterns limits its prediction performance. In this paper, motivated by this observation, we propose TopExpert to leverage topology-specific prediction models (referred to as experts), each of which is responsible for each molecular group sharing similar topological semantics. That is, each expert learns topology-specific discriminative features while being trained with its corresponding topological group. To tackle the key challenge of grouping molecules by their topological patterns, we introduce a clustering-based gating module that assigns an input molecule into one of the clusters and further optimizes the gating module with two different types of self-supervision: topological semantics induced by GNNs and molecular scaffolds, respectively. Extensive experiments demonstrate that TopExpert has boosted the performance for molecular property prediction and also achieved better generalization for new molecules with unseen scaffolds than baselines. The code is available at https://github.com/kimsu55/ToxExpert.

Spike camera, a new type of neuromorphic visual sensor that imitates the sampling mechanism of the primate fovea, can capture photons and output 40000 Hz binary spike streams. Benefiting from the asynchronous sampling mechanism, the spike camera can record fast-moving objects and clear images can be recovered from the spike stream at any specified timestamps without motion blurring. Despite these, due to the dense time sequence information of the discrete spike stream, it is not easy to directly apply the existing algorithms of traditional cameras to the spike camera. Therefore, it is necessary and interesting to explore a universally effective representation of dense spike streams to better fit various network architectures. In this paper, we propose to mine temporal-robust features of spikes in time-frequency space with wavelet transforms. We present a novel Wavelet-Guided Spike Enhancing (WGSE) paradigm consisting of three consecutive steps: multi-level wavelet transform, CNN-based learnable module, and inverse wavelet transform. With the assistance of WGSE, the new streaming representation of spikes can be learned. We demonstrate the effectiveness of WGSE on two downstream tasks, achieving state-of-the-art performance on the image reconstruction task and getting considerable performance on semantic segmentation. Furthermore, We build a new spike-based synthesized dataset for semantic segmentation. Code and Datasets are available at https://github.com/Leozhangjiyuan/WGSE-SpikeCamera.

By adopting popular pixel-wise loss, existing methods for defocus deblurring heavily rely on well aligned training image pairs. Although training pairs of ground-truth and blurry images are carefully collected, e.g., DPDD dataset, misalignment is inevitable between training pairs, making existing methods possibly suffer from deformation artifacts. In this paper, we propose a joint deblurring and reblurring learning (JDRL) framework for single image defocus deblurring with misaligned training pairs. Generally, JDRL consists of a deblurring module and a spatially invariant reblurring module, by which deblurred result can be adaptively supervised by ground-truth image to recover sharp textures while maintaining spatial consistency with the blurry image. First, in the deblurring module, a bi-directional optical flow-based deformation is introduced to tolerate spatial misalignment between deblurred and ground-truth images. Second, in the reblurring module, deblurred result is reblurred to be spatially aligned with blurry image, by predicting a set of isotropic blur kernels and weighting maps. Moreover, we establish a new single image defocus deblurring (SDD) dataset, further validating our JDRL and also benefiting future research. Our JDRL can be applied to boost defocus deblurring networks in terms of both quantitative metrics and visual quality on DPDD, RealDOF and our SDD datasets.

Simulations that produce three-dimensional data are ubiquitous in science, ranging from fluid flows to plasma physics. We propose a similarity model based on entropy, which allows for the creation of physically meaningful ground truth distances for the similarity assessment of scalar and vectorial data, produced from transport and motion-based simulations. Utilizing two data acquisition methods derived from this model, we create collections of fields from numerical PDE solvers and existing simulation data repositories. Furthermore, a multiscale CNN architecture that computes a volumetric similarity metric (VolSiM) is proposed. To the best of our knowledge this is the first learning method inherently designed to address the challenges arising for the similarity assessment of high-dimensional simulation data. Additionally, the tradeoff between a large batch size and an accurate correlation computation for correlation-based loss functions is investigated, and the metric's invariance with respect to rotation and scale operations is analyzed. Finally, the robustness and generalization of VolSiM is evaluated on a large range of test data, as well as a particularly challenging turbulence case study, that is close to potential real-world applications.

Low-light images suffer severe degradation of low lightness and noise corruption, causing unsatisfactory visual quality and visual recognition performance. To solve this problem while meeting the unavailability of paired datasets in wide-range scenarios, unsupervised low-light image enhancement (ULLIE) techniques have been developed. However, these methods are primarily guided to alleviate the degradation effect on visual quality rather than semantic levels, hence limiting their performance in visual recognition tasks. To this end, we propose to learn a Semantic Degradation-Aware Guidance (SDAG) that perceives the low-light degradation effect on semantic levels in a self-supervised manner, which is further utilized to guide the ULLIE methods. The proposed SDAG utilizes the low-light degradation factors as augmented signals to degrade the low-light images, and then capture their degradation effect on semantic levels. Specifically, our SDAG employs the subsequent pre-trained recognition model extractor to extract semantic representations, and then learns to self-reconstruct the enhanced low-light image and its augmented degraded images. By constraining the relative reconstruction effect between the original enhanced image and the augmented formats, our SDAG learns to be aware of the degradation effect on semantic levels in a relative comparison manner. Moreover, our SDAG is general and can be plugged into the training paradigm of the existing ULLIE methods. Extensive experiments demonstrate its effectiveness for improving the ULLIE approaches on the downstream recognition tasks while maintaining a competitive visual quality. Code will be available at https://github.com/zheng980629/SDAG.

Video-language pre-training for text-based video retrieval tasks is vitally important. Previous pre-training methods suffer from the semantic misalignments. The reason is that these methods ignore sequence alignments but focusing on critical token alignment. To alleviate the problem, we propose a video-language pre-training framework, termed videolanguage pre-training For lEarning sEmantic aLignments (FEEL), to learn semantic alignments at the sequence level. Specifically, the global modality reconstruction and the cross- modal self-contrasting method is utilized to learn the alignments at the sequence level better. Extensive experimental results demonstrate the effectiveness of FEEL on text-based video retrieval and text-based video corpus moment retrieval.

Correspondence pruning aims to search consistent correspondences (inliers) from a set of putative correspondences. It is challenging because of the disorganized spatial distribution of numerous outliers, especially when putative correspondences are largely dominated by outliers. It's more challenging to ensure effectiveness while maintaining efficiency. In this paper, we propose an effective and efficient method for correspondence pruning. Inspired by the success of attentive context in correspondence problems, we first extend the attentive context to the first-order attentive context and then introduce the idea of attention in attention (ANA) to model second-order attentive context for correspondence pruning. Compared with first-order attention that focuses on feature-consistent context, second-order attention dedicates to attention weights itself and provides an additional source to encode consistent context from the attention map. For efficiency, we derive two approximate formulations for the naive implementation of second-order attention to optimize the cubic complexity to linear complexity, such that second-order attention can be used with negligible computational overheads. We further implement our formulations in a second-order context layer and then incorporate the layer in an ANA block. Extensive experiments demonstrate that our method is effective and efficient in pruning outliers, especially in high-outlier-ratio cases. Compared with the state-of-the-art correspondence pruning approach LMCNet, our method runs 14 times faster while maintaining a competitive accuracy.

Powerful domain-independent planners have been developed to solve various types of planning problems. These planners often require a model of the acting agent's actions, given in some planning domain description language. Yet obtaining such an action model is a notoriously hard task. This task is even more challenging in mission-critical domains, where a trial-and-error approach to learning how to act is not an option. In such domains, the action model used to generate plans must be safe, in the sense that plans generated with it must be applicable and achieve their goals. Learning safe action models for planning has been recently explored for domains in which states are sufficiently described with Boolean variables. In this work, we go beyond this limitation and propose the NSAM algorithm. NSAM runs in time that is polynomial in the number of observations and, under certain conditions, is guaranteed to return safe action models. We analyze its worst-case sample complexity, which may be intractable for some domains. Empirically, however, NSAM can quickly learn a safe action model that can solve most problems in the domain.

We consider a seller faced with buyers which have the ability to delay their decision, which we call patience. Each buyer's type is composed of value and patience, and it is sampled i.i.d. from a distribution. The seller, using posted prices, would like to maximize her revenue from selling to the buyer. In this paper, we formalize this setting and characterize the resulting Stackelberg equilibrium, where the seller first commits to her strategy, and then the buyers best respond. Following this, we show how to compute both the optimal pure and mixed strategies. We then consider a learning setting, where the seller does not have access to the distribution over buyer's types. Our main results are the following. We derive a sample complexity bound for the learning of an approximate optimal pure strategy, by computing the fat-shattering dimension of this setting. Moreover, we provide a general sample complexity bound for the approximate optimal mixed strategy. We also consider an online setting and derive a vanishing regret bound with respect to both the optimal pure strategy and the optimal mixed strategy.

Knowledge graphs represent known facts using triplets. While existing knowledge graph embedding methods only consider the connections between entities, we propose considering the relationships between triplets. For example, let us consider two triplets T1 and T2 where T1 is (Academy_Awards, Nominates, Avatar) and T2 is (Avatar, Wins, Academy_Awards). Given these two base-level triplets, we see that T1 is a prerequisite for T2. In this paper, we define a higher-level triplet to represent a relationship between triplets, e.g., where PrerequisiteFor is a higher-level relation. We define a bi-level knowledge graph that consists of the base-level and the higher-level triplets. We also propose a data augmentation strategy based on the random walks on the bi-level knowledge graph to augment plausible triplets. Our model called BiVE learns embeddings by taking into account the structures of the base-level and the higher-level triplets, with additional consideration of the augmented triplets. We propose two new tasks: triplet prediction and conditional link prediction. Given a triplet T1 and a higher-level relation, the triplet prediction predicts a triplet that is likely to be connected to T1 by the higher-level relation, e.g., . The conditional link prediction predicts a missing entity in a triplet conditioned on another triplet, e.g., . Experimental results show that BiVE significantly outperforms all other methods in the two new tasks and the typical base-level link prediction in real-world bi-level knowledge graphs.

In real-world phenomena which involve mutual influence or causal effects between interconnected units, equilibrium states are typically represented with cycles in graphical models. An expressive class of graphical models, relational causal models, can represent and reason about complex dynamic systems exhibiting such cycles or feedback loops. Existing cyclic causal discovery algorithms for learning causal models from observational data assume that the data instances are independent and identically distributed which makes them unsuitable for relational causal models. At the same time, causal discovery algorithms for relational causal models assume acyclicity. In this work, we examine the necessary and sufficient conditions under which a constraint-based relational causal discovery algorithm is sound and complete for cyclic relational causal models. We introduce relational acyclification, an operation specifically designed for relational models that enables reasoning about the identifiability of cyclic relational causal models. We show that under the assumptions of relational acyclification and sigma-faithfulness, the relational causal discovery algorithm RCD is sound and complete for cyclic relational models. We present experimental results to support our claim.

We present a framework for learning useful subgoals that support efficient long-term planning to achieve novel goals. At the core of our framework is a collection of rational subgoals (RSGs), which are essentially binary classifiers over the environmental states. RSGs can be learned from weakly-annotated data, in the form of unsegmented demonstration trajectories, paired with abstract task descriptions, which are composed of terms initially unknown to the agent (e.g., collect-wood then craft-boat then go-across-river). Our framework also discovers dependencies between RSGs, e.g., the task collect-wood is a helpful subgoal for the task craft-boat. Given a goal description, the learned subgoals and the derived dependencies facilitate off-the-shelf planning algorithms, such as A* and RRT, by setting helpful subgoals as waypoints to the planner, which significantly improves performance-time efficiency. Project page: https://rsg.csail.mit.edu

Visible-Infrared Person Re-Identification (VI-ReID) is a challenging retrieval task under complex modality changes. Existing methods usually focus on extracting discriminative visual features while ignoring the reliability and commonality of visual features between different modalities. In this paper, we propose a novel deep learning framework named Progressive Modality-shared Transformer (PMT) for effective VI-ReID. To reduce the negative effect of modality gaps, we first take the gray-scale images as an auxiliary modality and propose a progressive learning strategy. Then, we propose a Modality-Shared Enhancement Loss (MSEL) to guide the model to explore more reliable identity information from modality-shared features. Finally, to cope with the problem of large intra-class differences and small inter-class differences, we propose a Discriminative Center Loss (DCL) combined with the MSEL to further improve the discrimination of reliable features. Extensive experiments on SYSU-MM01 and RegDB datasets show that our proposed framework performs better than most state-of-the-art methods. For model reproduction, we release the source code at https://github.com/hulu88/PMT.

We present a self-learning approach for synthesizing programs from integer sequences. Our method relies on a tree search guided by a learned policy. Our system is tested on the On-Line Encyclopedia of Integer Sequences. There, it discovers, on its own, solutions for 27987 sequences starting from basic operators and without human-written training examples.

Along with the widespread use of face recognition systems, their vulnerability has become highlighted. While existing face anti-spoofing methods can be generalized between attack types, generic solutions are still challenging due to the diversity of spoof characteristics. Recently, the spoof trace disentanglement framework has shown great potential for coping with both seen and unseen spoof scenarios, but the performance is largely restricted by the single-modal input. This paper focuses on this issue and presents a multi-modal disentanglement model which targetedly learns polysemantic spoof traces for more accurate and robust generic attack detection. In particular, based on the adversarial learning mechanism, a two-stream disentangling network is designed to estimate spoof patterns from the RGB and depth inputs, respectively. In this case, it captures complementary spoofing clues inhering in different attacks. Furthermore, a fusion module is exploited, which recalibrates both representations at multiple stages to promote the disentanglement in each individual modality. It then performs cross-modality aggregation to deliver a more comprehensive spoof trace representation for prediction. Extensive evaluations are conducted on multiple benchmarks, demonstrating that learning polysemantic spoof traces favorably contributes to anti-spoofing with more perceptible and interpretable results.