{"ID":2899475,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.00440","arxiv_id":"2507.00440","title":"A Recipe for Causal Graph Regression: Confounding Effects Revisited","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.","short_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 regres...","url_abs":"https://arxiv.org/abs/2507.00440","url_pdf":"https://arxiv.org/pdf/2507.00440v1","authors":"[\"Yujia Yin\",\"Tianyi Qu\",\"Zihao Wang\",\"Yifan Chen\"]","published":"2025-07-01T05:46:29Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"stat.ME\"]","methods":"[\"Graph Neural Network\"]","has_code":false,"code_links":[{"ID":612485,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2899475,"paper_url":"https://arxiv.org/abs/2507.00440","paper_title":"A Recipe for Causal Graph Regression: Confounding Effects Revisited","repo_url":"https://github.com/causal-graph/CGR","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}