mlsanityData to 14 Oct 2026

A Recipe for Causal Graph Regression: Confounding Effects Revisited

arXiv 2507.00440 ↗First posted 1 Jul 2025cs.LG cs.AI stat.MEcited by 3

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 35 of its 53 references that are in the map. First posted on arXiv 1 Jul 2025.

Builds on

35 of 53 references.

References · 35

  1. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  4. 2019Invariant Risk Minimizationcited by 1,854
  5. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,247
  6. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
  7. 2015Deep Learning and the Information Bottleneck Principlecited by 802
  8. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 765
  9. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 742
  10. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 652
  11. 2020Parameterized Explainer for Graph Neural Networkcited by 426
  12. 2019Deep Evidential Regressioncited by 355
23 more
  1. 2017Grammar Variational Autoencodercited by 285
  2. 2020Representation Learning via Invariant Causal Mechanismscited by 199
  3. 2022Discovering Invariant Rationales for Graph Neural Networkscited by 188
  4. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
  5. 2020Graph Information Bottleneckcited by 168
  6. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 164
  7. 2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144
  8. 2022GOOD: A Graph Out-of-Distribution Benchmarkcited by 141
  9. 2021Generative Causal Explanations for Graph Neural Networkscited by 124
  10. 2021Causal Attention for Interpretable and Generalizable Graph Classificationcited by 108
  11. 2022Debiasing Graph Neural Networks via Learning Disentangled Causal Substructurecited by 83
  12. 2021OOD-GNN: Out-of-Distribution Generalized Graph Neural Networkcited by 78
  13. 2021Generalizing Graph Neural Networks on Out-Of-Distribution Graphscited by 71
  14. 2023Does Invariant Graph Learning via Environment Augmentation Learn Invariance?cited by 42
  15. 2021No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasetscited by 31
  16. 2023Counterfactual Learning on Graphs: A Surveycited by 22
  17. 2022Robust Causal Graph Representation Learning against Confounding Effectscited by 12
  18. 2022Deconfounding to Explanation Evaluation in Graph Neural Networkscited by 10
  19. 2023RegExplainer: Generating Explanations for Graph Neural Networks in Regression Taskscited by 9
  20. 2024Cauchy-Schwarz Divergence Information Bottleneck for Regressioncited by 9
  21. 2023Towards out-of-distribution generalizable predictions of chemical kinetics propertiescited by 7
  22. 2024Causal Graph Neural Networks for Wildfire Danger Predictioncited by 7
  23. 2024A Survey of Out-of-distribution Generalization for Graph Machine Learning from a Causal Viewcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Peeling Context from Cause for Molecular Property Predictioncited by 0
  2. 2026Predicting Trajectories of Long COVID in Adult Women: The Critical Role of Causal Disentanglementcited by 0
  3. 2026SIR: Structured Image Representations for Explainable Robot Learningcited by 0