一作SIGIR 2026Oral· Information Retrieval (Full)
Inductive Subgraphs as Shortcuts: Causal Disentanglement for Heterophilic Graph Learning
Xiangmeng Wang · Qian Li · Haiyang Xia · Hao Miao · Li Qing · Guandong Xu
摘要
Heterophily is a prevalent property of real-world graphs and is well known to impair the performance of homophilic Graph Neural Networks (GNNs). Prior work has attempted to adapt GNNs to heterophilic graphs through non-local neighbor extension or architecture refinement. However, the fundamental...