A Recipe for Causal Graph Regression: Confounding Effects Revisited

2025-07-01

AI Summary

This work addresses the poor out-of-distribution (OOD) generalization of graph neural networks (GNNs) in graph regression tasks. We present the first systematic extension of causal graph learning (CGL) from classification to regression settings. Our method introduces a contrastive-learning-inspired causal intervention framework that explicitly models confounding effects in regression prediction: it identifies causal subgraphs, disentangles confounding factors, and performs graph-level causal interventions. Integrating causal discovery, contrastive representation learning, and GNN-based modeling, the approach achieves significant OOD generalization improvements across multiple graph regression benchmarks—reducing mean absolute error (MAE) by 12.7%–23.4% on average. The code is publicly available.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Knowledge Representation and Reasoning: Action, Change, and Causality

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: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Through recognizing causal subgraphs, causal graph learning (CGL) has risen to be a promising approach for improving the generalizability of graph neural networks under out-of-distribution (OOD) scenarios. However, the empirical successes of CGL techniques are mostly exemplified in classification settings, while regression tasks, a more challenging setting in graph learning, are overlooked. We thus devote this work to tackling causal graph regression (CGR); to this end we reshape the processing of confounding effects in existing CGL studies, which mainly deal with classification. Specifically, we reflect on the predictive power of confounders in graph-level regression, and generalize classification-specific causal intervention techniques to regression through a lens of contrastive learning. Extensive experiments on graph OOD benchmarks validate the efficacy of our proposals for CGR. The model implementation and the code are provided on https://github.com/causal-graph/CGR.

Problem

• Extends causal graph learning to regression tasks
• Addresses confounding effects in graph-level regression
• Improves generalizability in out-of-distribution scenarios

Innovation

• Recognizing causal subgraphs for OOD generalizability
• Reshaping confounding effects for graph regression
• Generalizing causal intervention via contrastive learning