计算机科学
下部结构
图形
图同构
人工智能
理论计算机科学
人工神经网络
图形属性
电压图
折线图
结构工程
工程类
作者
Jianliang Gao,Jun Gao,Xiaoting Ying,Mingming Lu,Jianxin Wang
出处
期刊:IEEE Transactions on Knowledge and Data Engineering
[Institute of Electrical and Electronics Engineers]
日期:2021-01-01
卷期号:: 1-1
被引量:15
标识
DOI:10.1109/tkde.2021.3105544
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, that play 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). 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.
科研通智能强力驱动
Strongly Powered by AbleSci AI