图神经网络（GNNs）已在图分类任务中取得了出色的成果，但在面对分布外（OOD）数据时难以实现有效泛化。目前已有多种方法被提出用于解决这一问题。其中一类方案是通过修改数据环境来拓展普通分类的训练分布，但获取环境信息的过程十分复杂。此外，另一类颇具潜力的方法是合理化方法，即提取用于预测的不变合理化依据。但由于学习信号有限，提取合理化依据的难度较大，会导致依据准确性不足、预测效果下降。为应对这些挑战，本文提出了协同分类与合理化（Cooperative Classification and Rationalization, C2R）方法，该方法由分类模块和合理化模块组成。具体而言，我们首先假设分类模块中存在多个可用环境，随后引入环境条件生成网络来构建多样化的训练分布，以得到鲁棒的图表示。同时，合理化模块使用分离器识别相关的依据子图，同时让剩余的非依据子图与标签去相关。接下来，我们利用知识蒸馏方法将分类模块输出的图表示与依据子图表示进行对齐，增强合理化依据的学习信号。最后，我们通过聚合非依据表示推断出多个环境，并将其融入分类模块以实现协同学习。在基准数据集和合成数据集上开展的大量实验结果证明了C2R的有效性。相关代码可在https://github.com/yuelinan/Codes-of-C2R获取。
英文摘要：
Graph Neural Networks (GNNs) have achieved impressive results in graph classification tasks, but they struggle to generalize effectively when faced with out-of-distribution (OOD) data. Several approaches have been proposed to address this problem. Among them, one solution is to diversify training distributions in vanilla classification by modifying the data environment, yet accessing the environment information is complex. Besides, another promising approach involves rationalization, extracting invariant rationales for predictions. However, extracting rationales is difficult due to limited learning signals, resulting in less accurate rationales and diminished predictions. To address these challenges, in this paper, we propose a Cooperative Classification and Rationalization (C2R) method, consisting of the classification and the rationalization module. Specifically, we first assume that multiple environments are available in the classification module. Then, we introduce diverse training distributions using an environment-conditional generative network, enabling robust graph representations. Meanwhile, the rationalization module employs a separator to identify relevant rationale subgraphs while the remaining non-rationale subgraphs are de-correlated with labels. Next, we align graph representations from the classification module with rationale subgraph representations using the knowledge distillation methods, enhancing the learning signal for rationales. Finally, we infer multiple environments by gathering non-rationale representations and incorporate them into the classification module for cooperative learning. Extensive experimental results on both benchmarks and synthetic datasets demonstrate the effectiveness of C2R. Code is available at https://github.com/yuelinan/Codes-of-C2R.
MIT-IBM Watson AI Lab（MIT-IBM沃森人工智能实验室）；CSAIL MIT（麻省理工学院计算机科学与人工智能实验室）；UC Santa Barbara（加州大学圣巴巴拉分校）
Selective rationalization explains the prediction of complex neural networks by finding a small subset of the input that is sufficient to predict the neural model output. The selection mechanism is commonly integrated into the model itself by specifying a two-component cascaded system consisting of a rationale generator, which makes a binary selection of the input features (which is the rationale), and a predictor, which predicts the output based only on the selected features. The components are trained jointly to optimize prediction performance. In this paper, we reveal a major problem with s…
IBM Research（IBM研究院）；MIT（麻省理工学院）；MIT-IBM Watson AI Lab（MIT-IBM沃森人工智能实验室）
Selective rationalization has become a common mechanism to ensure that predictive models reveal how they use any available features. The selection may be soft or hard, and identifies a subset of input features relevant for prediction. The setup can be viewed as a co-operate game between the selector (aka rationale generator) and the predictor making use of only the selected features. The co-operative setting may, however, be compromised for two reasons. First, the generator typically has no direct access to the outcome it aims to justify, resulting in poor performance. Second, there's typicall…
Imperial College London（帝国理工学院）；Technical University of Munich（慕尼黑工业大学）；Klinikum rechts der Isar（伊萨尔河右岸医院）；University of Edinburgh（爱丁堡大学）
Deep learning-based segmentation methods are vulnerable to unforeseen data distribution shifts during deployment, e.g. change of image appearances or contrasts caused by different scanners, unexpected imaging artifacts etc. In this paper, we present a cooperative framework for training image segmentation models and a latent space augmentation method for generating hard examples. Both contributions improve model generalization and robustness with limited data. The cooperative training framework consists of a fast-thinking network (FTN) and a slow-thinking network (STN). The FTN learns decoupled…
The Cooperative Network Architecture: Learning Structured Networks as Representation of Sensory Patterns
Zurich University of Applied Sciences（苏黎世应用科学大学）；University of Zurich（苏黎世大学）；ETH Zurich（苏黎世联邦理工学院）；Frankfurt Institute for Advanced Studies（法兰克福高级研究 institute）
Multi-population Ensemble Genetic Programming via Cooperative Coevolution and Multi-view Learning for Classification
Faculty of Engineering & Information Technology, University of Technology Sydney（工程与信息科技学院，技术悉尼大学）；Department of Civil and Architectural Engineering, Sultan Qaboos University（土木与建筑工程系，苏丹·卡布斯大学）；University Research and Innovation Center (EKIK), Obuda University（研究与创新中心（EKIK），奥布达大学）
The Chinese University of Hong Kong（香港中文大学）；Tencent AI Lab（腾讯人工智能实验室）；Hong Kong Baptist University（香港浸会大学）
Recently, there has been a growing surge of interest in enabling machine learning systems to generalize well to Out-of-Distribution (OOD) data. Most efforts are devoted to advancing optimization objectives that regularize models to capture the underlying invariance; however, there often are compromises in the optimization process of these OOD objectives: i) Many OOD objectives have to be relaxed as penalty terms of Empirical Risk Minimization (ERM) for the ease of optimization, while the relaxed forms can weaken the robustness of the original objective; ii) The penalty terms also require caref…
University of Oxford（牛津大学）；University College London（伦敦大学学院）；Meta AI
Collective intelligence is a fundamental trait shared by several species of living organisms. It has allowed them to thrive in the diverse environmental conditions that exist on our planet. From simple organisations in an ant colony to complex systems in human groups, collective intelligence is vital for solving complex survival tasks. As is commonly observed, such natural systems are flexible to changes in their structure. Specifically, they exhibit a high degree of generalization when the abilities or the total number of agents changes within a system. We term this phenomenon as Combinatoria…
University Of Science And Technology Of China（中国科学技术大学）
Recommender systems are often susceptible to well-crafted fake profiles, leading to biased recommendations. The wide application of recommender systems makes studying the defense against attack necessary. Among existing defense methods, data-processing-based methods inevitably exclude normal samples, while model-based methods struggle to enjoy both generalization and robustness. Considering the above limitations, we suggest integrating data processing and robust model and propose a general framework, Triple Cooperative Defense (TCD), which cooperates to improve model robustness through the co-…
Bridging Classification and Reconstruction: Cooperative Time Series Anomaly Detection
National Key Laboratory of Information Systems Engineering, National University of Defense Technology（信息系统工程国家重点实验室，国防科技大学）；College of Systems Engineering, National University of Defense Technology（系统工程学院，国防科技大学）；Zhejiang University（浙江大学）；Zhejiang Key Laboratory of Space Information Sensing and Transmission, Hangzhou Dianzi University（空间信息感知与传输浙江大学重点实验室，杭州电子科技大学）
Facebook（脸书）；Lamsade, Univ. Paris Dauphine（巴黎多芬纳大学Lamsade实验室）
Effective coordination is crucial to solve multi-agent collaborative (MAC) problems. While centralized reinforcement learning methods can optimally solve small MAC instances, they do not scale to large problems and they fail to generalize to scenarios different from those seen during training. In this paper, we consider MAC problems with some intrinsic notion of locality (e.g., geographic proximity) such that interactions between agents and tasks are locally limited. By leveraging this property, we introduce a novel structured prediction approach to assign agents to tasks. At each step, the as…
Visible light positioning (VLP) has drawn plenty of attention as a promising indoor positioning technique. However, in nonstationary environments, the performance of VLP is limited because of the highly time-varying channels. To improve the positioning accuracy and generalization capability in nonstationary environments, a cooperative VLP scheme based on federated learning (FL) is proposed in this paper. Exploiting the FL framework, a global model adaptive to environmental changes can be jointly trained by users without sharing private data of users. Moreover, a Cooperative Visible-light Posit…
A Cascading Cooperative Multi-agent Framework for On-ramp Merging Control Integrating Large Language Models
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Department of Computer Science & Engineering, University of Minnesota（明尼苏达大学计算机科学与工程系）；Department of Mechanical Engineering & Materials Science, Yale University（耶鲁大学机械工程与材料科学系）；Computer Vision, BYD COMPANY LIMITED（计算机视觉，比亚迪有限公司）；School of Architecture, University of Texas at Austin（德克萨斯大学奥斯汀分校建筑学院）；Faculty of Applied Science & Engineering, University of Toronto（多伦多大学应用科学与工程学院）
The University of Hong Kong（香港大学）；Shenzhen Research Institute of Big Data（深圳大数据研究院）；Tongji University（同济大学）
Cooperative beamforming design has been recognized as an effective approach in modern wireless networks to meet the dramatically increasing demand of various wireless data traffics. It is formulated as an optimization problem in conventional approaches and solved iteratively in an instance-by-instance manner. Recently, learning-based methods have emerged with real-time implementation by approximating the mapping function from the problem instances to the corresponding solutions. Among various neural network architectures, graph neural networks (GNNs) can effectively utilize the graph topology …
University of Science and Technology of China（中国科学技术大学）；National University of Singapore（新加坡国立大学）
Intrinsic interpretability of graph neural networks (GNNs) is to find a small subset of the input graph's features -- rationale -- which guides the model prediction. Unfortunately, the leading rationalization models often rely on data biases, especially shortcut features, to compose rationales and make predictions without probing the critical and causal patterns. Moreover, such data biases easily change outside the training distribution. As a result, these models suffer from a huge drop in interpretability and predictive performance on out-of-distribution data. In this work, we propose a new s…
Achieving and maintaining cooperation between agents to accomplish a common objective is one of the central goals of Multi-Agent Reinforcement Learning (MARL). Nevertheless in many real-world scenarios, separately trained and specialized agents are deployed into a shared environment, or the environment requires multiple objectives to be achieved by different coexisting parties. These variations among specialties and objectives are likely to cause mixed motives that eventually result in a social dilemma where all the parties are at a loss. In order to resolve this issue, we propose the Incentiv…
While multi-agent interactions can be naturally modeled as a graph, the environment has traditionally been considered as a black box. We propose to create a shared agent-entity graph, where agents and environmental entities form vertices, and edges exist between the vertices which can communicate with each other. Agents learn to cooperate by exchanging messages along the edges of this graph. Our proposed multi-agent reinforcement learning framework is invariant to the number of agents or entities present in the system as well as permutation invariance, both of which are desirable properties fo…
A framework for the emergence and analysis of language in social learning agents
Johannes Gutenberg-University Mainz（美因茨约翰内斯·古腾堡大学）；Technical University Darmstadt（达姆施塔特工业大学）；University of Bonn Medical Center（波恩大学医学中心）；Max-Planck Institute for Brain Research（马克斯·普朗克大脑研究所）
In this work, we analyze the generalization ability of distributed online learning algorithms under stationary and non-stationary environments. We derive bounds for the excess-risk attained by each node in a connected network of learners and study the performance advantage that diffusion strategies have over individual non-cooperative processing. We conduct extensive simulations to illustrate the results.
