Inductive Subgraphs as Shortcuts: Causal Disentanglement for Heterophilic Graph Learning

TL;DR

This paper identifies that recurring inductive subgraphs act as spurious shortcuts in heterophilic graphs, and proposes a causal inference-based framework, CD-GNN, to improve GNN robustness and accuracy by disentangling causal from non-causal subgraphs.

Contribution

It introduces a causal perspective to analyze and mitigate shortcut biases in heterophilic GNNs, proposing the CD-GNN framework for improved node classification.

Findings

CD-GNN outperforms state-of-the-art heterophily-aware baselines.

Theoretical analysis confirms inductive subgraphs as spurious shortcuts.

Experiments validate the effectiveness of causal disentanglement in heterophilic graphs.

Abstract

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.