Introducing diminutive causal structure into graph representation learning

Hang Gao, Peng Qiao, Yifan Jin, Fengge Wu, Jiangmeng Li, Changwen Zheng

Abstract: Highlights•Discovered that introducing diminutive causal structures can enhance performance.•A novel method for introducing diminutive causal structures into GNN models.•Thorough theoretical analysis and substantiation regarding the studied problem.•Comprehensive validation of the proposed method through multiple experiments.