Community-influencing path explanation for link prediction in heterogeneous graph neural network

Yanhong Wen, Yuhua Li, Yixiong Zou, Kai Shu, Han Chen, Ziwen Zhao, Jinxian Ye, Quan Fu, Ruixuan Li

Abstract: Highlights•Communities effectiveness in GNN explanations for heterogeneous link prediction is first studied.•A community-influencing GNN explanation model for heterogeneous link prediction is proposed.•Proposed community-influencing objective guides the learning process by community.•Extensive experiments on four heterogeneous datasets demonstrate the effectiveness of method.