Causal Neighbourhood Learning for Invariant Graph Representations

2026-02-20

AI Summary

This work addresses the limited generalization of graph neural networks (GNNs) under distribution shifts, which stems from noise and spurious correlations in graphs obscuring true causal relationships. To tackle this, the authors propose CNL-GNN, a novel framework that uniquely integrates structural-level causal intervention with feature disentanglement. By generating counterfactual neighborhoods, introducing learnable importance masks, and leveraging attention mechanisms, CNL-GNN adaptively perturbs edge connections to explicitly model causal neighborhoods and effectively separate causal features from confounding factors. Extensive experiments on four public cross-domain datasets demonstrate that the proposed method significantly outperforms existing approaches, validating its effectiveness in enhancing representation invariance, robustness, and generalization under distributional shifts.

Technology Category

• Machine Learning: Causal Learning
• Knowledge Representation and Reasoning: Action, Change, and Causality
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Graph data often contain noisy and spurious correlations that mask the true causal relationships, which are essential for enabling graph models to make predictions based on the underlying causal structure of the data. Dependence on spurious connections makes it challenging for traditional Graph Neural Networks (GNNs) to generalize effectively across different graphs. Furthermore, traditional aggregation methods tend to amplify these spurious patterns, limiting model robustness under distribution shifts. To address these issues, we propose Causal Neighbourhood Learning with Graph Neural Networks (CNL-GNN), a novel framework that performs causal interventions on graph structure. CNL-GNN effectively identifies and preserves causally relevant connections and reduces spurious influences through the generation of counterfactual neighbourhoods and adaptive edge perturbation guided by learnable importance masking and an attention-based mechanism. In addition, by combining structural-level interventions with the disentanglement of causal features from confounding factors, the model learns invariant node representations that are robust and generalize well across different graph structures. Our approach improves causal graph learning beyond traditional feature-based methods, resulting in a robust classification model. Extensive experiments on four publicly available datasets, including multiple domain variants of one dataset, demonstrate that CNL-GNN outperforms state-of-the-art GNN models.

Problem

• causal relationships
• spurious correlations
• graph neural networks
• distribution shifts
• invariant representations

Innovation

• Causal Neighbourhood Learning
• Counterfactual Neighbourhoods
• Invariant Graph Representations
• Edge Perturbation
• Disentangled Causal Features