Graph Neural Networks (GNNs) learn low dimensional representations of nodes by aggregating information from their neighborhood in graphs. However, traditional GNNs suffer from two fundamental shortcomings due to their local ($l$-hop neighborhood) aggregation scheme. First, not all nodes in the neighborhood carry relevant information for the target node. Since GNNs do not exclude noisy nodes in their neighborhood, irrelevant information gets aggregated, which reduces the quality of the representation. Second, traditional GNNs also fail to capture long-range non-local dependencies between nodes. To address these limitations, we exploit mutual information (MI) to define two types of neighborhood, 1) \textit{Local Neighborhood} where nodes are densely connected within a community and each node would share higher MI with its neighbors, and 2) \textit{Non-Local Neighborhood} where MI-based node clustering is introduced to assemble informative but graphically distant nodes in the same cluster. To generate node presentations, we combine the embeddings generated by bi-level aggregation - local aggregation to aggregate features from local neighborhoods to avoid noisy information and non-local aggregation to aggregate features from non-local neighborhoods. Furthermore, we leverage self-supervision learning to estimate MI with few labeled data. Finally, we show that our model significantly outperforms the state-of-the-art methods in a wide range of assortative and disassortative graphs.
MIARec: Mutual-influence-aware Heterogeneous Network Embedding for Scientific Paper Recommendation
College of Computer and Information Science, Southwest university（西南大学计算机与信息科学学院）；College of Computer and Information Science, Chongqing normal university（重庆师范大学计算机与信息科学学院）
$\rm A^2Q$: Aggregation-Aware Quantization for Graph Neural Networks
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Shanghai Jiao Tong University（上海交通大学）
Beyond the Aggregation Dilemma: Prior-Retaining Decoupled Learning for Multimodal Graphs
School of Computer Science and Engineering, Central South University（中南大学计算机科学与工程学院）；Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University（香港理工大学数据科学与人工智能系）；School of Information and Communication Technology, Griffith University（格里菲斯大学信息与通信技术学院）
What Makes Effective Supervision in Latent Chain-of-Thought: An Information-Theoretic Analysis
Ningbo Institute of Digital Twin, Eastern Institute of Technology（宁波数字孪生研究院，东方理工大学）；Department of Computing, The Hong Kong Polytechnic University（香港理工大学计算学系）
Sentence Bag Graph Formulation for Biomedical Distant Supervision Relation Extraction
School of Computer Science and Technology, Harbin Institute of Technology（哈尔滨工业大学计算机科学与技术学院）；University of Rochester（罗切斯特大学）；School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture（北京建筑大学电气与信息工程学院）；Beijing Key Laboratory of Intelligent Processing for Building Big Data, Beijing University of Civil Engineering and Architecture（北京建筑大学北京市建筑大数据智能处理重点实验室）
Efficient Process Reward Modeling via Contrastive Mutual Information
Department of Electrical and Computer Engineering, Seoul National University（首尔大学电气与计算机工程系）；Department of Computer Science and Engineering, Konkuk University（建国大学计算机科学与工程系）
