提出动态同质性度量，揭示GNN在动态图中性能下降原因
Understanding GNNs and Homophily in Dynamic Node Classification
- 基于未来标签与当前邻居标签一致性定义动态同质性
- 实验证明低动态同质性下GNN性能显著下降
- 适合研究动态图学习、GNN鲁棒性问题的学者参考
同质性作为理解图神经网络（GNN）的重要指标，此前仅在静态图中被分析。本文首次在动态图场景下探索同质性，聚焦图卷积网络（GCN），理论上证明其判别性能取决于节点未来标签与邻居当前标签相同的概率。基于此，提出适用于动态场景的新同质性度量——动态同质性，该度量与GNN判别性能高度相关，并为设计更强大的动态图GNN提供思路。利用多个动态节点分类数据集，实验表明主流GNN在低动态同质性下表现不佳。本工作推动了对动态节点分类中同质性与GNN性能关系的理解。
原文摘要 · Abstract (English)
Homophily, as a measure, has been critical to increasing our understanding of graph neural networks (GNNs). However, to date this measure has only been analyzed in the context of static graphs. In our work, we explore homophily in dynamic settings. Focusing on graph convolutional networks (GCNs), we demonstrate theoretically that in dynamic settings, current GCN discriminative performance is characterized by the probability that a node's future label is the same as its neighbors' current labels. Based on this insight, we propose dynamic homophily, a new measure of homophily that applies in the dynamic setting. This new measure correlates with GNN discriminative performance and sheds light on how to potentially design more powerful GNNs for dynamic graphs. Leveraging a variety of dynamic node classification datasets, we demonstrate that popular GNNs are not robust to low dynamic homophily. Going forward, our work represents an important step towards understanding homophily and GNN performance in dynamic node classification.
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。