AAAI 2023 论文列表

Multi-instance learning (MIL) is a supervised learning where each example is a labeled bag with many instances. The typical MIL strategies are to train an instance-level feature extractor followed by aggregating instances features as bag-level representation with labeled information. However, learning such a bag-level representation highly depends on a large number of labeled datasets, which are difficult to get in real-world scenarios. In this paper, we make the first attempt to propose a robust Self-supervised Multi-Instance LEarning architecture with Structure awareness (SMILEs) that learns unsupervised bag representation. Our proposed approach is: 1) permutation invariant to the order of instances in bag; 2) structure-aware to encode the topological structures among the instances; and 3) robust against instances noise or permutation. Specifically, to yield robust MIL model without label information, we augment the multi-instance bag and train the representation encoder to maximize the correspondence between the representations of the same bag in its different augmented forms. Moreover, to capture topological structures from nearby instances in bags, our framework learns optimal graph structures for the bags and these graphs are optimized together with message passing layers and the ordered weighted averaging operator towards contrastive loss. Our main theorem characterizes the permutation invariance of the bag representation. Compared with state-of-the-art supervised MIL baselines, SMILEs achieves average improvement of 4.9%, 4.4% in classification accuracy on 5 benchmark datasets and 20 newsgroups datasets, respectively. In addition, we show that the model is robust to the input corruption.

Recent work has shown that representation learning plays a critical role in sample-efficient reinforcement learning (RL) from pixels. Unfortunately, in real-world scenarios, representation learning is usually fragile to task-irrelevant distractions such as variations in background or viewpoint. To tackle this problem, we propose a novel clustering-based approach, namely Clustering with Bisimulation Metrics (CBM), which learns robust representations by grouping visual observations in the latent space. Specifically, CBM alternates between two steps: (1) grouping observations by measuring their bisimulation distances to the learned prototypes; (2) learning a set of prototypes according to the current cluster assignments. Computing cluster assignments with bisimulation metrics enables CBM to capture task-relevant information, as bisimulation metrics quantify the behavioral similarity between observations. Moreover, CBM encourages the consistency of representations within each group, which facilitates filtering out task-irrelevant information and thus induces robust representations against distractions. An appealing feature is that CBM can achieve sample-efficient representation learning even if multiple distractions exist simultaneously. Experiments demonstrate that CBM significantly improves the sample efficiency of popular visual RL algorithms and achieves state-of-the-art performance on both multiple and single distraction settings. The code is available at https://github.com/MIRALab-USTC/RL-CBM.

In 2020, maternal mortality in India was estimated to be as high as 130 deaths per 100K live births, nearly twice the UN's target. To improve health outcomes, the non-profit ARMMAN sends automated voice messages to expecting and new mothers across India. However, 38% of mothers stop listening to these calls, missing critical preventative care information. To improve engagement, ARMMAN employs health workers to intervene by making service calls, but workers can only call a fraction of the 100K enrolled mothers. Partnering with ARMMAN, we model the problem of allocating limited interventions across mothers as a restless multi-armed bandit (RMAB), where the realities of large scale and model uncertainty present key new technical challenges. We address these with GROUPS, a double oracle–based algorithm for robust planning in RMABs with scalable grouped arms. Robustness over grouped arms requires several methodological advances. First, to adversarially select stochastic group dynamics, we develop a new method to optimize Whittle indices over transition probability intervals. Second, to learn group-level RMAB policy best responses to these adversarial environments, we introduce a weighted index heuristic. Third, we prove a key theoretical result that planning over grouped arms achieves the same minimax regret--optimal strategy as planning over individual arms, under a technical condition. Finally, using real-world data from ARMMAN, we show that GROUPS produces robust policies that reduce minimax regret by up to 50%, halving the number of preventable missed voice messages to connect more mothers with life-saving maternal health information.

One-shot segmentation of brain tissues is typically a dual-model iterative learning: a registration model (reg-model) warps a carefully-labeled atlas onto unlabeled images to initialize their pseudo masks for training a segmentation model (seg-model); the seg-model revises the pseudo masks to enhance the reg-model for a better warping in the next iteration. However, there is a key weakness in such dual-model iteration that the spatial misalignment inevitably caused by the reg-model could misguide the seg-model, which makes it converge on an inferior segmentation performance eventually. In this paper, we propose a novel image-aligned style transformation to reinforce the dual-model iterative learning for robust one-shot segmentation of brain tissues. Specifically, we first utilize the reg-model to warp the atlas onto an unlabeled image, and then employ the Fourier-based amplitude exchange with perturbation to transplant the style of the unlabeled image into the aligned atlas. This allows the subsequent seg-model to learn on the aligned and style-transferred copies of the atlas instead of unlabeled images, which naturally guarantees the correct spatial correspondence of an image-mask training pair, without sacrificing the diversity of intensity patterns carried by the unlabeled images. Furthermore, we introduce a feature-aware content consistency in addition to the image-level similarity to constrain the reg-model for a promising initialization, which avoids the collapse of image-aligned style transformation in the first iteration. Experimental results on two public datasets demonstrate 1) a competitive segmentation performance of our method compared to the fully-supervised method, and 2) a superior performance over other state-of-the-art with an increase of average Dice by up to 4.67%. The source code is available at: https://github.com/JinxLv/One-shot-segmentation-via-IST.

Goal Recognition is the task of discerning the intended goal of an agent given a sequence of observations, whereas Plan Recognition consists of identifying the plan to achieve such intended goal. Regardless of the underlying techniques, most recognition approaches are directly affected by the quality of the available observations. In this paper, we develop neuro-symbolic recognition approaches that can combine learning and planning techniques, compensating for noise and missing observations using prior data. We evaluate our approaches in standard human-designed planning domains as well as domain models automatically learned from real-world data. Empirical experimentation shows that our approaches reliably infer goals and compute correct plans in the experimental datasets. An ablation study shows that outperform approaches that rely exclusively on the domain model, or exclusively on machine learning in problems with both noisy observations and low observability.

Cooperative Multi-agent Reinforcement Learning (CMARL) has shown to be promising for many real-world applications. Previous works mainly focus on improving coordination ability via solving MARL-specific challenges (e.g., non-stationarity, credit assignment, scalability), but ignore the policy perturbation issue when testing in a different environment. This issue hasn't been considered in problem formulation or efficient algorithm design. To address this issue, we firstly model the problem as a Limited Policy Adversary Dec-POMDP (LPA-Dec-POMDP), where some coordinators from a team might accidentally and unpredictably encounter a limited number of malicious action attacks, but the regular coordinators still strive for the intended goal. Then, we propose Robust Multi-Agent Coordination via Evolutionary Generation of Auxiliary Adversarial Attackers (ROMANCE), which enables the trained policy to encounter diversified and strong auxiliary adversarial attacks during training, thus achieving high robustness under various policy perturbations. Concretely, to avoid the ego-system overfitting to a specific attacker, we maintain a set of attackers, which is optimized to guarantee the attackers high attacking quality and behavior diversity. The goal of quality is to minimize the ego-system coordination effect, and a novel diversity regularizer based on sparse action is applied to diversify the behaviors among attackers. The ego-system is then paired with a population of attackers selected from the maintained attacker set, and alternately trained against the constantly evolving attackers. Extensive experiments on multiple scenarios from SMAC indicate our ROMANCE provides comparable or better robustness and generalization ability than other baselines.

Steganography is a technique that hides secret messages into a public multimedia object without raising suspicion from third parties. However, most existing works cannot provide good robustness against lossy JPEG compression while maintaining a relatively large embedding capacity. This paper presents an end-to-end robust steganography system based on the invertible neural network (INN). Instead of hiding in the spatial domain, our method directly hides secret messages into the discrete cosine transform (DCT) coefficients of the cover image, which significantly improves the robustness and anti-steganalysis security. A mutual information loss is first proposed to constrain the flow of information in INN. Besides, a two-way fusion module (TWFM) is implemented, utilizing spatial and DCT domain features as auxiliary information to facilitate message extraction. These two designs aid in recovering secret messages from the DCT coefficients losslessly. Experimental results demonstrate that our method yields significantly lower error rates than other existing hiding methods. For example, our method achieves reliable extraction with 0 error rate for 1 bit per pixel (bpp) embedding payload; and under the JPEG compression with quality factor QF=10, the error rate of our method is about 22% lower than the state-of-the-art robust image hiding methods, which demonstrates remarkable robustness against JPEG compression.

Images taken in low light conditions typically contain distracting noise, and eliminating such noise is a crucial computer vision problem. Additional photos captured with a camera flash can guide an image denoiser to preserve edges since the flash images often contain fine details with reduced noise. Nonetheless, a denoiser can be misled by inconsistent flash images, which have image structures (e.g., edges) that do not exist in no-flash images. Unfortunately, this disparity frequently occurs as the flash/no-flash pairs are taken in different light conditions. We propose a learning-based technique that robustly fuses the image pairs while considering their inconsistency. Our framework infers consistent flash image patches locally, which have similar image structures with the ground truth, and denoises no-flash images using the inferred ones via a combination model. We demonstrate that our technique can produce more robust results than state-of-the-art methods, given various flash/no-flash pairs with inconsistent image structures. The source code is available at https://github.com/CGLab-GIST/RIDFnF.

Graph meta-learning has become a preferable paradigm for graph-based node classification with long-tail distribution, owing to its capability of capturing the intrinsic manifold of support and query nodes. Despite the remarkable success, graph meta-learning suffers from severe performance degradation when training on graph data with structural noise. In this work, we observe that the structural noise may impair the smoothness of the intrinsic manifold supporting the support and query nodes, leading to the poor transferable priori of the meta-learner. To address the issue, we propose a new approach for graph meta-learning that is robust against structural noise, called Proxy subgraph-based Manifold Calibration method (Pro-MC). Concretely, a subgraph generator is designed to generate proxy subgraphs that can calibrate the smoothness of the manifold. The proxy subgraph compromises two types of subgraphs with two biases, thus preventing the manifold from being rugged and straightforward. By doing so, our proposed meta-learner can obtain generalizable and transferable prior knowledge. In addition, we provide a theoretical analysis to illustrate the effectiveness of Pro-MC. Experimental results have demonstrated that our approach can achieve state-of-the-art performance under various structural noises.

Pretrained vision models for object recognition often suffer a dramatic performance drop with degradations unseen during training. In this work, we propose a RObust FEature Rectification module (ROFER) to improve the performance of pretrained models against degradations. Specifically, ROFER first estimates the type and intensity of the degradation that corrupts the image features. Then, it leverages a Fully Convolutional Network (FCN) to rectify the features from the degradation by pulling them back to clear features. ROFER is a general-purpose module that can address various degradations simultaneously, including blur, noise, and low contrast. Besides, it can be plugged into pretrained models seamlessly to rectify the degraded features without retraining the whole model. Furthermore, ROFER can be easily extended to address composite degradations by adopting a beam search algorithm to find the composition order. Evaluations on CIFAR-10 and Tiny-ImageNet demonstrate that the accuracy of ROFER is 5% higher than that of SOTA methods on different degradations. With respect to composite degradations, ROFER improves the accuracy of a pretrained CNN by 10% and 6% on CIFAR-10 and Tiny-ImageNet respectively.

Most domain adaptation methods for machine reading comprehension (MRC) use a pre-trained question-answer (QA) construction model to generate pseudo QA pairs for MRC transfer. Such a process will inevitably introduce mismatched pairs (i.e., Noisy Correspondence) due to i) the unavailable QA pairs in target documents, and ii) the domain shift during applying the QA construction model to the target domain. Undoubtedly, the noisy correspondence will degenerate the performance of MRC, which however is neglected by existing works. To solve such an untouched problem, we propose to construct QA pairs by additionally using the dialogue related to the documents, as well as a new domain adaptation method for MRC. Specifically, we propose Robust Domain Adaptation for Machine Reading Comprehension (RMRC) method which consists of an answer extractor (AE), a question selector (QS), and an MRC model. Specifically, RMRC filters out the irrelevant answers by estimating the correlation to the document via the AE, and extracts the questions by fusing the candidate questions in multiple rounds of dialogue chats via the QS. With the extracted QA pairs, MRC is fine-tuned and provides the feedback to optimize the QS through a novel reinforced self-training method. Thanks to the optimization of the QS, our method will greatly alleviate the noisy correspondence problem caused by the domain shift. To the best of our knowledge, this could be the first study to reveal the influence of noisy correspondence in domain adaptation MRC models and show a feasible solution to achieve the robustness against the mismatched pairs. Extensive experiments on three datasets demonstrate the effectiveness of our method.

The prevailing graph neural network models have achieved significant progress in graph representation learning. However, in this paper, we uncover an ever-overlooked phenomenon: the pre-trained graph representation learning model tested with full graphs underperforms the model tested with well-pruned graphs. This observation reveals that there exist confounders in graphs, which may interfere with the model learning semantic information, and current graph representation learning methods have not eliminated their influence. To tackle this issue, we propose Robust Causal Graph Representation Learning (RCGRL) to learn robust graph representations against confounding effects. RCGRL introduces an active approach to generate instrumental variables under unconditional moment restrictions, which empowers the graph representation learning model to eliminate confounders, thereby capturing discriminative information that is causally related to downstream predictions. We offer theorems and proofs to guarantee the theoretical effectiveness of the proposed approach. Empirically, we conduct extensive experiments on a synthetic dataset and multiple benchmark datasets. Experimental results demonstrate the effectiveness and generalization ability of RCGRL. Our codes are available at https://github.com/hang53/RCGRL.

In robust Markov decision processes (MDPs), the uncertainty in the transition kernel is addressed by finding a policy that optimizes the worst-case performance over an uncertainty set of MDPs. While much of the literature has focused on discounted MDPs, robust average-reward MDPs remain largely unexplored. In this paper, we focus on robust average-reward MDPs, where the goal is to find a policy that optimizes the worst-case average reward over an uncertainty set. We first take an approach that approximates average-reward MDPs using discounted MDPs. We prove that the robust discounted value function converges to the robust average-reward as the discount factor goes to 1, and moreover when it is large, any optimal policy of the robust discounted MDP is also an optimal policy of the robust average-reward. We further design a robust dynamic programming approach, and theoretically characterize its convergence to the optimum. Then, we investigate robust average-reward MDPs directly without using discounted MDPs as an intermediate step. We derive the robust Bellman equation for robust average-reward MDPs, prove that the optimal policy can be derived from its solution, and further design a robust relative value iteration algorithm that provably finds its solution, or equivalently, the optimal robust policy.

In this work, we present a novel risk-aware decentralized Control Barrier Function (CBF)-based controller for multi-agent systems. The proposed decentralized controller is composed based on pairwise agent responsibility shares (a percentage), calculated from the risk evaluation of each individual agent faces in a multi-agent interaction environment. With our proposed CBF-inspired risk evaluation framework, the responsibility portions between pairwise agents are dynamically updated based on the relative risk they face. Our method allows agents with lower risk to enjoy a higher level of freedom in terms of a wider action space, and the agents exposed to higher risk are constrained more tightly on action spaces, and are therefore forced to proceed with caution.

Time series is the most prevalent form of input data for educational prediction tasks. The vast majority of research using time series data focuses on hand-crafted features, designed by experts for predictive performance and interpretability. However, extracting these features is labor-intensive for humans and computers. In this paper, we propose an approach that utilizes irregular multivariate time series modeling with graph neural networks to achieve comparable or better accuracy with raw time series clickstreams in comparison to hand-crafted features. Furthermore, we extend concept activation vectors for interpretability in raw time series models. We analyze these advances in the education domain, addressing the task of early student performance prediction for downstream targeted interventions and instructional support. Our experimental analysis on 23 MOOCs with millions of combined interactions over six behavioral dimensions show that models designed with our approach can (i) beat state-of-the-art educational time series baselines with no feature extraction and (ii) provide interpretable insights for personalized interventions. Source code: https://github.com/epfl-ml4ed/ripple/.

The Symmetric Positive Definite (SPD) matrices have received wide attention for data representation in many scientific areas. Although there are many different attempts to develop effective deep architectures for data processing on the Riemannian manifold of SPD matrices, very few solutions explicitly mine the local geometrical information in deep SPD feature representations. Given the great success of local mechanisms in Euclidean methods, we argue that it is of utmost importance to ensure the preservation of local geometric information in the SPD networks. We first analyse the convolution operator commonly used for capturing local information in Euclidean deep networks from the perspective of a higher level of abstraction afforded by category theory. Based on this analysis, we define the local information in the SPD manifold and design a multi-scale submanifold block for mining local geometry. Experiments involving multiple visual tasks validate the effectiveness of our approach.

Script is a kind of structured knowledge extracted from texts, which contains a sequence of events. Based on such knowledge, script event prediction aims to predict the subsequent event. To do so, two aspects should be considered for events, namely, event description (i.e., what the events should contain) and event encoding (i.e., how they should be encoded). Most existing methods describe an event by a verb together with a few core arguments (i.e., subject, object, and indirect object), which are not precise enough. In addition, existing event encoders are limited to a fixed number of arguments, which are not flexible enough to deal with extra information. Thus, in this paper, we propose the Rich Event Prediction (REP) framework for script event prediction. Fundamentally, it is based on the proposed rich event description, which enriches the existing ones with three kinds of important information, namely, the senses of verbs, extra semantic roles, and types of participants. REP contains an event extractor to extract such information from texts. Based on the extracted rich information, a predictor then selects the most probable subsequent event. The core component of the predictor is a transformer-based event encoder that integrates the above information flexibly. Experimental results on the widely used Gigaword Corpus show the effectiveness of the proposed framework.

Reward-biased maximum likelihood estimation (RBMLE) is a classic principle in the adaptive control literature for tackling explore-exploit trade-offs. This paper studies the neural contextual bandit problem from a distributional perspective and proposes NeuralRBMLE, which leverages the likelihood of surrogate parametric distributions to learn the unknown reward distributions and thereafter adapts the RBMLE principle to achieve efficient exploration by properly adding a reward-bias term. NeuralRBMLE leverages the representation power of neural networks and directly encodes exploratory behavior in the parameter space, without constructing confidence intervals of the estimated rewards. We propose two variants of NeuralRBMLE algorithms: The first variant directly obtains the RBMLE estimator by gradient ascent, and the second variant simplifies RBMLE to a simple index policy through an approximation. We show that both algorithms achieve order-optimality. Through extensive experiments, we demonstrate that the NeuralRBMLE algorithms achieve comparable or better empirical regrets than the state-of-the-art methods on real-world datasets with non-linear reward functions.

This study proposed a novel reward-based negotiating agent strategy using an issue-based represented deep policy network. We compared the negotiation strategies with reinforcement learning (RL) by the tournaments toward heuristics-based champion agents in multi-issue negotiation. A bilateral multi-issue negotiation in which the two agents exchange offers in turn was considered. Existing RL architectures for a negotiation strategy incorporate rich utility function that provides concrete information even though the rewards of RL are considered as generalized signals in practice. Additionally, in existing reinforcement learning architectures for negotiation strategies, both the issue-based representations of the negotiation problems and the policy network to improve the scalability of negotiation domains are yet to be considered. This study proposed a novel reward-based negotiation strategy through deep RL by considering an issue-based represented deep policy network for multi-issue negotiation. Comparative studies analyzed the significant properties of negotiation strategies with RL. The results revealed that the policy-based learning agents with issue-based representations achieved comparable or higher utility than the state-of-the-art baselines with RL and heuristics, especially in the large-sized domains. Additionally, negotiation strategies with RL based on the policy network can achieve agreements by effectively using each step.