Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Inductive Subgraphs as Shortcuts: Causal Disentanglement for Heterophilic Graph Learning

About

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. In this work, we take a novel perspective by examining recurring inductive subgraphs, empirically and theoretically showing that they act as spurious shortcuts that mislead GNNs and reinforce non-causal correlations in heterophilic graphs. To address this, we adopt a causal inference perspective to analyze and correct the biased learning behavior induced by shortcut inductive subgraphs. We propose a debiased causal graph that explicitly blocks confounding and spillover paths responsible for these shortcuts. Guided by this causal graph, we introduce Causal Disentangled GNN (CD-GNN), a principled framework that disentangles spurious inductive subgraphs from true causal subgraphs by explicitly blocking non-causal paths. By focusing on genuine causal signals, CD-GNN substantially improves the robustness and accuracy of node classification in heterophilic graphs. Extensive experiments on real-world datasets not only validate our theoretical findings but also demonstrate that our proposed CD-GNN outperforms state-of-the-art heterophily-aware baselines.

Xiangmeng Wang, Qian Li, Haiyang Xia, Hao Miao, Qing Li, Guandong Xu• 2026

Related benchmarks

TaskDatasetResultRank
Node ClassificationChameleon
Accuracy67.62
867
Node ClassificationCornell
Accuracy72.97
851
Node ClassificationSquirrel
Accuracy58.98
786
Node ClassificationRoman-Empire
Accuracy65.85
327
Node Classificationamazon-ratings
Accuracy44.51
309
Node ClassificationComputers
Accuracy88.48
145
Node Classificationquestions
Accuracy97.2
64
Showing 7 of 7 rows

Other info

Follow for update