mlsanityData to 7 Oct 2026

Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalization

arXiv 2306.01103 ↗First posted 1 Jun 2023cs.LG cs.AIcited by 29

Not on the map. Why?

Abstract (arXiv)

We tackle the problem of graph out-of-distribution (OOD) generalization. Existing graph OOD algorithms either rely on restricted assumptions or fail to exploit environment information in training data. In this work, we propose to simultaneously incorporate label and environment causal independence (LECI) to fully make use of label and environment information, thereby addressing the challenges faced by prior methods on identifying causal and invariant subgraphs. We further develop an adversarial training strategy to jointly optimize these two properties for causal subgraph discovery with theoretical guarantees. Extensive experiments and analysis show that LECI significantly outperforms prior methods on both synthetic and real-world datasets, establishing LECI as a practical and effective solution for graph OOD generalization. Our code is available at https://github.com/divelab/LECI.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 96 of its 125 references that are in the map. First posted on arXiv 1 Jun 2023.

Builds on

96 of 125 references.

References · 96

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2017Graph Attention Networkscited by 8,854
  5. 2022Generative Adversarial Networkscited by 5,603
  6. 2018How Powerful are Graph Neural Networks?cited by 4,355
  7. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  8. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  9. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  10. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  11. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  12. 2019Invariant Risk Minimizationcited by 1,832
38 more
  1. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  2. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  3. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  4. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  5. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  6. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  7. 2019A Comprehensive Survey on Transfer Learningcited by 1,154
  8. 2020In Search of Lost Domain Generalizationcited by 1,042
  9. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
  10. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  11. 2020Learning to Simulate Complex Physics with Graph Networkscited by 867
  12. 2015Deep Learning and the Information Bottleneck Principlecited by 793
  13. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  14. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  15. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  16. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
  17. 2018Deep Visual Domain Adaptation: A Surveycited by 634
  18. 2013Domain Generalization via Invariant Feature Representationcited by 622
  19. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  20. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 533
  21. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 503
  22. 2019Graph U-Netscited by 489
  23. 2020Principal Neighbourhood Aggregation for Graph Netscited by 477
  24. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  25. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  26. 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
  27. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
  28. 2018A Survey of Unsupervised Deep Domain Adaptationcited by 361
  29. 2018Learning Models with Uniform Performance via Distributionally Robust Optimizationcited by 334
  30. 2019Analysing Mathematical Reasoning Abilities of Neural Modelscited by 331
  31. 2020Environment Inference for Invariant Learningcited by 306
  32. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 280
  33. 2020The Risks of Invariant Risk Minimizationcited by 262
  34. 2018Graph networks as learnable physics engines for inference and controlcited by 242
  35. 2021Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalizationcited by 220
  36. 2020How Neural Networks Extrapolate: From Feedforward to Graph Neural Networkscited by 218
  37. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
  38. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209

50 most cited of 96 All 96 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 13; 2025: 9; 2026: 3.

29 papers.

Sort:

By area:

  1. 2024A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challengescited by 54
  2. 2023Does Invariant Graph Learning via Environment Augmentation Learn Invariance?cited by 42
  3. 2024Pairwise Alignment Improves Graph Domain Adaptationcited by 25
  4. 2024Equivariance via Minimal Frame Averaging for More Symmetries and Efficiencycited by 18
  5. 2024A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptationcited by 16
  6. 2024Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNscited by 14
  7. 2024How Interpretable Are Interpretable Graph Neural Networks?cited by 13
  8. 2024Is the MMI Criterion Necessary for Interpretability? Degenerating Non-causal Features to Plain Noise for Self-Rationalizationcited by 11
  9. 2023Graph Structure and Feature Extrapolation for Out-of-Distribution Generalizationcited by 10
  10. 2023Identifying Semantic Component for Robust Molecular Property Predictioncited by 10
  11. 2025Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspectivecited by 10
  12. 2024Out-of-Distribution Learning with Human Feedbackcited by 6
17 more
  1. 2025Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilizationcited by 6
  2. 2025Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasetscited by 6
  3. 2024Spatio-Temporal Fluid Dynamics Modeling via Physical-Awareness and Parameter Diffusion Guidancecited by 5
  4. 2023When Graph Neural Network Meets Causality: Opportunities, Methodologies and An Outlookcited by 4
  5. 2024A Survey of Out-of-distribution Generalization for Graph Machine Learning from a Causal Viewcited by 3
  6. 2024Virtual Nodes Can Help: Tackling Distribution Shifts in Federated Graph Learningcited by 3
  7. 2025Pruning Spurious Subgraphs for Graph Out-of-Distribution Generalizationcited by 3
  8. 2025Measure-Theoretic Anti-Causal Representation Learningcited by 3
  9. 2024Invariant Graph Learning Meets Information Bottleneck for Out-of-Distribution Generalizationcited by 2
  10. 2025Quantifying Distributional Invariance in Causal Subgraph for IRM-Free Graph Generalizationcited by 2
  11. 2025Evolving Graph Learning for Out-of-Distribution Generalization in Non-stationary Environmentscited by 2
  12. 2026SCL-GNN: Towards Generalizable Graph Neural Networks via Spurious Correlation Learningcited by 1
  13. 2024Improving Graph Out-of-distribution Generalization Beyond Causalitycited by 0
  14. 2025Catch Causal Signals from Edges for Label Imbalance in Graph Classificationcited by 0
  15. 2025Out-of-Distribution Graph Models Mergingcited by 0
  16. 2026Rethinking Graph Generalization through the Lens of Sharpness-Aware Minimizationcited by 0
  17. 2026Structure-agnostic Causal Representation Learningcited by 0