Higher-Order Interaction Goes Neural: A Substructure Assembling Graph Attention Network for Graph Classification

IEEE Transactions on Knowledge and Data Engineering(2023)

引用 21|浏览85
暂无评分
摘要
Graph classification has been widely used for knowledge discovery in numerous practical application scenarios, such as social networks and protein-protein interaction networks. Recently, Graph Neural Networks (GNNs), which generalize deep neural networks to graph-structured data, have drawn considerable attention and achieved state-of-the-art performance in graph classification. However, existing GNN models mainly focus on capturing the information of immediate or first-order neighboring nodes within a single layer. The graph substructure and substructure interaction, which plays an important role in learning graph representations, are usually overlooked. In this paper, we propose a Substructure Assembling Graph Attention Network (SA-GAT) to extract graph features and improve the performance of graph classification. SA-GAT is able to fully explore higher-order substructure information hidden in graphs by a core module called Substructure Interaction Attention (SIA), which takes both the information of neighbors’ substructures and the interaction information among them into account during aggregation process. Theoretically, we have also proved that SA-GAT satisfies the graph isomorphism theory of graph neural network design, which is that the network should map isomorphic graphs to the same representation and output the same prediction. Extensive experimental results on multiple real-world graph classification datasets demonstrate that the proposed SA-GAT outperforms the state-of-the-art methods including graph kernels and graph neural networks.
更多
查看译文
关键词
Graph classification,graph attention networks,higher-order graph,substructure interaction
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