mlsanityData to 14 Oct 2026

Evolving Graph Learning for Out-of-Distribution Generalization in Non-stationary Environments

arXiv 2511.02354 ↗First posted 4 Nov 2025cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Graph neural networks have shown remarkable success in exploiting the spatial and temporal patterns on dynamic graphs. However, existing GNNs exhibit poor generalization ability under distribution shifts, which is inevitable in dynamic scenarios. As dynamic graph generation progresses amid evolving latent non-stationary environments, it is imperative to explore their effects on out-of-distribution (OOD) generalization. This paper proposes a novel Evolving Graph Learning framework for OOD generalization (EvoOOD) by environment-aware invariant pattern recognition. Specifically, we first design an environment sequential variational auto-encoder to model environment evolution and infer the underlying environment distribution. Then, we introduce a mechanism for environment-aware invariant pattern recognition, tailored to address environmental diversification through inferred distributions. Finally, we conduct fine-grained causal interventions on individual nodes using a mixture of instantiated environment samples. This approach helps to distinguish spatio-temporal invariant patterns for OOD prediction, especially in non-stationary environments. Experimental results demonstrate the superiority of EvoGOOD on both real-world and synthetic dynamic datasets under distribution shifts. To the best of our knowledge, it is the first attempt to study the dynamic graph OOD generalization problem from the environment evolution perspective.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 61 of its 100 references that are in the map. First posted on arXiv 4 Nov 2025.

Builds on

61 of 100 references.

References · 61

  1. 2017Graph Attention Networkscited by 8,923
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  3. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  4. 2019Invariant Risk Minimizationcited by 1,854
  5. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,850
  6. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,247
  7. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  8. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 742
  9. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 494
  10. 2019Predicting Dynamic Embedding Trajectory in Temporal Interaction Networkscited by 448
  11. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 447
  12. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
38 more
  1. 2017Certifying Some Distributional Robustness with Principled Adversarial Trainingcited by 337
  2. 2020Environment Inference for Invariant Learningcited by 306
  3. 2016Structured Sequence Modeling with Graph Convolutional Recurrent Networkscited by 275
  4. 2020The Risks of Invariant Risk Minimizationcited by 262
  5. 2021A Comprehensive Survey on Graph Anomaly Detection with Deep Learningcited by 230
  6. 2020Graph Random Neural Network for Semi-Supervised Learning on Graphscited by 213
  7. 2020Data Augmentation for Graph Neural Networkscited by 203
  8. 2020Representation Learning via Invariant Causal Mechanismscited by 199
  9. 2020Invariant Risk Minimization Gamescited by 188
  10. 2022Discovering Invariant Rationales for Graph Neural Networkscited by 188
  11. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
  12. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 164
  13. 2022G-Mixup: Graph Data Augmentation for Graph Classificationcited by 146
  14. 2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144
  15. 2022GOOD: A Graph Out-of-Distribution Benchmarkcited by 141
  16. 2020Invariant Rationalizationcited by 131
  17. 2021Generative Causal Explanations for Graph Neural Networkscited by 124
  18. 2018Invariance, Causality and Robustnesscited by 123
  19. 2021Causal Attention for Interpretable and Generalizable Graph Classificationcited by 108
  20. 2021Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Datacited by 87
  21. 2021Size-Invariant Graph Representations for Graph Classification Extrapolationscited by 84
  22. 2022Debiasing Graph Neural Networks via Learning Disentangled Causal Substructurecited by 83
  23. 2020Factorizable Graph Convolutional Networkscited by 79
  24. 2021OOD-GNN: Out-of-Distribution Generalized Graph Neural Networkcited by 78
  25. 2021Generalizing Graph Neural Networks on Out-Of-Distribution Graphscited by 71
  26. 2022Graph Rationalization with Environment-based Augmentationscited by 70
  27. 2020Learning Invariant Representations and Risks for Semi-supervised Domain Adaptationcited by 69
  28. 2021Learning from Counterfactual Links for Link Predictioncited by 69
  29. 2020Robust Optimization as Data Augmentation for Large-scale Graphscited by 58
  30. 2022Let Invariant Rationale Discovery Inspire Graph Contrastive Learningcited by 57
  31. 2021Local Augmentation for Graph Neural Networkscited by 53
  32. 2019Independence Promoted Graph Disentangled Networkscited by 38
  33. 2022OOD Link Prediction Generalization Capabilities of Message-Passing GNNs in Larger Test Graphscited by 38
  34. 2022SizeShiftReg: a Regularization Method for Improving Size-Generalization in Graph Neural Networkscited by 37
  35. 2023Mind the Label Shift of Augmentation-based Graph OOD Generalizationcited by 34
  36. 2024Graph Out-of-Distribution Generalization via Causal Interventioncited by 31
  37. 2022WOODS: Benchmarks for Out-of-Distribution Generalization in Time Seriescited by 30
  38. 2022Metropolis-Hastings Data Augmentation for Graph Neural Networkscited by 30

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspectivecited by 4
  2. 2026When Can You Correct Distribution Drift in Temporal Graph Generation? A Sharpening--Drift Tension and an Impossibility for Observation-Based Correctioncited by 0