SSHPool: The Separated Subgraph-based Hierarchical Pooling

In this paper, we develop a novel local graph pooling method, namely the Separated Subgraph-based Hierarchical Pooling (SSHPool), for graph classification. We commence by assigning the nodes of a sample graph into different clusters, resulting in a family of separated subgraphs. We individually employ the local graph convolution units as the local structure to further compress each subgraph into a coarsened node, transforming the original graph into a coarsened graph. Since these subgraphs are separated by different clusters and the structural information cannot be propagated between them, the local convolution operation can significantly avoid the over-smoothing problem caused by message passing through edges in most existing Graph Neural Networks (GNNs). By hierarchically performing the proposed procedures on the resulting coarsened graph, the proposed SSHPool can effectively extract the hierarchical global features of the original graph structure, encapsulating rich intrinsic structural characteristics. Furthermore, we develop an end-to-end GNN framework associated with the SSHPool module for graph classification. Experimental results demonstrate the superior performance of the proposed model on real-world datasets.

Authors

• Zhuo Xu National University of Defense Technology
• Lu Bai School of Artificial Intelligence, and Engineering Research Center of Intelligent Technology and Educational Application, Ministry of Education, Beijing Normal University
• Lixin Cui School of Information, Central University of Finance and Economics, Beijing, China
• Ming Li
• Hangyuan Du School of Computer and Information Technology, Shanxi University, Taiyuan, China
• Ziyu Lyu School of Cyber Science and Technology, Sun Yat-Sen University, Shenzhen, China
• Yue Wang University of Central Florida
• Edwin R. Hancock University of York

Keywords

No keywords are indexed for this paper.