Improving Expressivity of GNNs with Subgraph-specific Factor Embedded Normalization

PROCEEDINGS OF THE 29TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2023(2023)

引用 0|浏览13
暂无评分
摘要
Graph Neural Networks (GNNs) have emerged as a powerful category of learning architecture for handling graph-structured data. However, existing GNNs typically ignore crucial structural characteristics in node-induced subgraphs, which thus limits their expressiveness for various downstream tasks. In this paper, we strive to strengthen the representative capabilities of GNNs by devising a dedicated plug-and-play normalization scheme, termed as SUbgraph-sPEcific FactoR Embedded Normalization (SuperNorm), that explicitly considers the intra-connection information within each node-induced subgraph. To this end, we embed the subgraph-specific factor at the beginning and the end of the standard BatchNorm, as well as incorporate graph instance-specific statistics for improved distinguishable capabilities. In the meantime, we provide theoretical analysis to support that, with the elaborated SuperNorm, an arbitrary GNN is at least as powerful as the 1-WL test in distinguishing non-isomorphism graphs. Furthermore, the proposed SuperNorm scheme is also demonstrated to alleviate the over-smoothing phenomenon. Experimental results related to predictions of graph, node, and link properties on the eight popular datasets demonstrate the effectiveness of the proposed method. The code is available at https://github.com/chenchkx/SuperNorm.
更多
查看译文
关键词
graph neural networks,graph normalization,subgraph-specific factor,graph isomorphism test,oversmoothing issue
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要