通过自适应重连边，提升异质图中长距离依赖捕捉能力
Exploring Adaptive Structure Learning for Heterophilic Graphs
- 参数化邻接矩阵，动态学习非局部节点间连接
- 在异质图上显著缓解了浅层GCN的过平滑问题
- 适合结构差异大的异质图场景，尤其关注长程依赖
图卷积网络（GCNs）在图表示学习中广受欢迎，近期研究聚焦于提升其在异质图上的性能，以应对多种真实应用场景。典型的消息传递范式存在局部特征聚合，难以捕捉同类别远距离节点间的长程依赖。异质图中的固有连接结构常与同类远距离节点间的信息共享相冲突。本文提出结构学习方法，在浅层GCN中重连边，避免因过平滑导致下游判别任务性能下降。通过参数化邻接矩阵，学习非局部节点间的连接，并扩展浅层GCN的跳数范围，从而更好地捕捉长程依赖。然而，该方法在不同异质图上泛化性有限，节点分类任务表现受图结构影响较大。
原文摘要 · Abstract (English)
Graph Convolutional Networks (GCNs) gained traction for graph representation learning, with recent attention on improving performance on heterophilic graphs for various real-world applications. The localized feature aggregation in a typical message-passing paradigm hinders the capturing of long-range dependencies between non-local nodes of the same class. The inherent connectivity structure in heterophilic graphs often conflicts with information sharing between distant nodes of same class. We propose structure learning to rewire edges in shallow GCNs itself to avoid performance degradation in downstream discriminative tasks due to oversmoothing. Parameterizing the adjacency matrix to learn connections between non-local nodes and extend the hop span of shallow GCNs facilitates the capturing of long-range dependencies. However, our method is not generalizable across heterophilic graphs and performs inconsistently on node classification task contingent to the graph structure.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。