Inductive Subgraphs as Shortcuts: Causal Disentanglement for Heterophilic Graph Learning

ArXi:2604.19186v1 Announce Type: cross 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 reasons behind misclassifications remain poorly understood.