mlsanityData to 14 Oct 2026

DeCaf: A Causal Decoupling Framework for OOD Generalization on Node Classification

arXiv 2410.20295 ↗First posted 27 Oct 2024cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) are susceptible to distribution shifts, creating vulnerability and security issues in critical domains. There is a pressing need to enhance the generalizability of GNNs on out-of-distribution (OOD) test data. Existing methods that target learning an invariant (feature, structure)-label mapping often depend on oversimplified assumptions about the data generation process, which do not adequately reflect the actual dynamics of distribution shifts in graphs. In this paper, we introduce a more realistic graph data generation model using Structural Causal Models (SCMs), allowing us to redefine distribution shifts by pinpointing their origins within the generation process. Building on this, we propose a casual decoupling framework, DeCaf, that independently learns unbiased feature-label and structure-label mappings. We provide a detailed theoretical framework that shows how our approach can effectively mitigate the impact of various distribution shifts. We evaluate DeCaf across both real-world and synthetic datasets that demonstrate different patterns of shifts, confirming its efficacy in enhancing the generalizability of GNNs.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 41 of its 62 references that are in the map. First posted on arXiv 27 Oct 2024.

Builds on

41 of 62 references.

References · 41

  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. 2019Simplifying Graph Convolutional Networkscited by 1,477
  6. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,247
  7. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  8. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 742
  9. 2015Image-based Recommendations on Styles and Substitutescited by 706
  10. 2013Domain Generalization via Invariant Feature Representationcited by 623
  11. 2015Estimation and Inference of Heterogeneous Treatment Effects using Random Forestscited by 600
  12. 2019Multi-scale Attributed Node Embeddingcited by 548
29 more
  1. 2017Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learningcited by 478
  2. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
  3. 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 343
  4. 2016Learning Representations for Counterfactual Inferencecited by 329
  5. 2019Adapting Neural Networks for the Estimation of Treatment Effectscited by 287
  6. 2020Invariant Risk Minimization Gamescited by 188
  7. 2022Discovering Invariant Rationales for Graph Neural Networkscited by 188
  8. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 164
  9. 2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144
  10. 2022GOOD: A Graph Out-of-Distribution Benchmarkcited by 141
  11. 2021Towards a Theoretical Framework of Out-of-Distribution Generalizationcited by 94
  12. 2021Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Datacited by 87
  13. 2020Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networkscited by 78
  14. 2021OOD-GNN: Out-of-Distribution Generalized Graph Neural Networkcited by 78
  15. 2021Generalizing Graph Neural Networks on Out-Of-Distribution Graphscited by 71
  16. 2023Energy-based Out-of-Distribution Detection for Graph Neural Networkscited by 68
  17. 2019Estimating Treatment Effects with Causal Forests: An Applicationcited by 58
  18. 2018Stable Prediction across Unknown Environmentscited by 55
  19. 2020DecAug: Out-of-Distribution Generalization via Decomposed Feature Representation and Semantic Augmentationcited by 48
  20. 2016Double/Debiased Machine Learning for Treatment and Causal Parameterscited by 43
  21. 2018DeepMatch: Balancing Deep Covariate Representations for Causal Inference Using Adversarial Trainingcited by 42
  22. 2021Causal Effect Inference for Structured Treatmentscited by 39
  23. 2019Independence Promoted Graph Disentangled Networkscited by 38
  24. 2022SizeShiftReg: a Regularization Method for Improving Size-Generalization in Graph Neural Networkscited by 37
  25. 2020Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designscited by 25
  26. 2022Debiased Graph Neural Networks with Agnostic Label Selection Biascited by 25
  27. 2020GraphITE: Estimating Individual Effects of Graph-structured Treatmentscited by 18
  28. 2022Deconfounding to Explanation Evaluation in Graph Neural Networkscited by 10
  29. 2024Learning Invariant Representations of Graph Neural Networks via Cluster Generalizationcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decompositioncited by 1
  2. 2026Exploring Concept Subspace for Self-explainable Text-Attributed Graph Learningcited by 0