Search papers, labs, and topics across Lattice.
The paper identifies recurring inductive subgraphs as spurious shortcuts that mislead GNNs on heterophilic graphs by reinforcing non-causal correlations. To address this, they propose a debiased causal graph that blocks confounding and spillover paths responsible for these shortcuts. Based on this causal graph, they introduce Causal Disentangled GNN (CD-GNN), which disentangles spurious inductive subgraphs from true causal subgraphs by explicitly blocking non-causal paths, leading to improved node classification accuracy and robustness.
GNN performance on heterophilic graphs suffers because of inductive subgraphs acting as spurious shortcuts, a problem that can be solved by causally disentangling these subgraphs.
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.
