mlsanityData to 14 Oct 2026

A Survey of Out-of-distribution Generalization for Graph Machine Learning from a Causal View

arXiv 2409.09858 ↗First posted 15 Sep 2024cs.LG cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

Graph machine learning (GML) has been successfully applied across a wide range of tasks. Nonetheless, GML faces significant challenges in generalizing over out-of-distribution (OOD) data, which raises concerns about its wider applicability. Recent advancements have underscored the crucial role of causality-driven approaches in overcoming these generalization challenges. Distinct from traditional GML methods that primarily rely on statistical dependencies, causality-focused strategies delve into the underlying causal mechanisms of data generation and model prediction, thus significantly improving the generalization of GML across different environments. This paper offers a thorough review of recent progress in causality-involved GML generalization. We elucidate the fundamental concepts of employing causality to enhance graph model generalization and categorize the various approaches, providing detailed descriptions of their methodologies and the connections among them. Furthermore, we explore the incorporation of causality in other related important areas of trustworthy GML, such as explanation, fairness, and robustness. Concluding with a discussion on potential future research directions, this review seeks to articulate the continuing development and future potential of causality in enhancing the trustworthiness of graph machine learning.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 51 of its 73 references that are in the map. First posted on arXiv 15 Sep 2024.

Builds on

51 of 73 references.

References · 51

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  4. 2019Invariant Risk Minimizationcited by 1,854
  5. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  6. 2016Variational Graph Auto-Encoderscited by 1,382
  7. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
  8. 2017Counterfactual Fairnesscited by 804
  9. 2019Graph Transformer Networkscited by 523
  10. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
  11. 2020Environment Inference for Invariant Learningcited by 306
  12. 2020Representation Learning via Invariant Causal Mechanismscited by 199
38 more
  1. 2022Discovering Invariant Rationales for Graph Neural Networkscited by 188
  2. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
  3. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 164
  4. 2020Conformal Inference of Counterfactuals and Individual Treatment Effectscited by 151
  5. 2019Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifierscited by 144
  6. 2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144
  7. 2021Generative Causal Explanations for Graph Neural Networkscited by 124
  8. 2022Causal Machine Learning: A Survey and Open Problemscited by 110
  9. 2021Causal Attention for Interpretable and Generalizable Graph Classificationcited by 108
  10. 2022Out-Of-Distribution Generalization on Graphs: A Surveycited by 97
  11. 2021Size-Invariant Graph Representations for Graph Classification Extrapolationscited by 84
  12. 2022Debiasing Graph Neural Networks via Learning Disentangled Causal Substructurecited by 83
  13. 2020Molecular graph generation with Graph Neural Networkscited by 80
  14. 2022Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoningcited by 79
  15. 2021A Review on Graph Neural Network Methods in Financial Applicationscited by 78
  16. 2021OOD-GNN: Out-of-Distribution Generalized Graph Neural Networkcited by 78
  17. 2022Fairness in Graph Mining: A Surveycited by 76
  18. 2021Generalizing Graph Neural Networks on Out-Of-Distribution Graphscited by 71
  19. 2022Graph Rationalization with Environment-based Augmentationscited by 70
  20. 2021Learning from Counterfactual Links for Link Predictioncited by 69
  21. 2022Let Invariant Rationale Discovery Inspire Graph Contrastive Learningcited by 57
  22. 2022CLEAR: Generative Counterfactual Explanations on Graphscited by 48
  23. 2023Does Invariant Graph Learning via Environment Augmentation Learn Invariance?cited by 42
  24. 2013Stochastic blockmodel approximation of a graphon: Theory and consistent estimationcited by 39
  25. 2022OOD Link Prediction Generalization Capabilities of Message-Passing GNNs in Larger Test Graphscited by 38
  26. 2024Graph Out-of-Distribution Generalization via Causal Interventioncited by 31
  27. 2023Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalizationcited by 29
  28. 2022Debiased Graph Neural Networks with Agnostic Label Selection Biascited by 25
  29. 2022A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protectioncited by 20
  30. 2023Learning Invariant Molecular Representation in Latent Discrete Spacecited by 19
  31. 2024Spectral Invariant Learning for Dynamic Graphs under Distribution Shiftscited by 19
  32. 2023Graph Invariant Learning with Subgraph Co-mixup for Out-Of-Distribution Generalizationcited by 18
  33. 2021Assessing the Causal Impact of COVID-19 Related Policies on Outbreak Dynamics: A Case Study in the UScited by 16
  34. 2023CI-GNN: A Granger Causality-Inspired Graph Neural Network for Interpretable Brain Network-Based Psychiatric Diagnosiscited by 16
  35. 2022Robust Causal Graph Representation Learning against Confounding Effectscited by 12
  36. 2022Deconfounding to Explanation Evaluation in Graph Neural Networkscited by 10
  37. 2023Exploring Causal Learning through Graph Neural Networks: An In-depth Reviewcited by 8
  38. 2023IDEA: Invariant Defense for Graph Adversarial Robustnesscited by 4

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 2.

3 papers.

  1. 2024A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptationcited by 17
  2. 2025A Recipe for Causal Graph Regression: Confounding Effects Revisitedcited by 3
  3. 2025Exploring Graph-Transformer Out-of-Distribution Generalization Abilitiescited by 1