mlsanityData to 14 Oct 2026

Non-stationary Domain Generalization: Theory and Algorithm

arXiv 2405.06816 ↗First posted 10 May 2024cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Although recent advances in machine learning have shown its success to learn from independent and identically distributed (IID) data, it is vulnerable to out-of-distribution (OOD) data in an open world. Domain generalization (DG) deals with such an issue and it aims to learn a model from multiple source domains that can be generalized to unseen target domains. Existing studies on DG have largely focused on stationary settings with homogeneous source domains. However, in many applications, domains may evolve along a specific direction (e.g., time, space). Without accounting for such non-stationary patterns, models trained with existing methods may fail to generalize on OOD data. In this paper, we study domain generalization in non-stationary environment. We first examine the impact of environmental non-stationarity on model performance and establish the theoretical upper bounds for the model error at target domains. Then, we propose a novel algorithm based on adaptive invariant representation learning, which leverages the non-stationary pattern to train a model that attains good performance on target domains. Experiments on both synthetic and real data validate the proposed algorithm.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 39 of its 54 references that are in the map. First posted on arXiv 10 May 2024.

Builds on

39 of 54 references.

References · 39

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  6. 2019Invariant Risk Minimizationcited by 1,854
  7. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
  8. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
  9. 2018Efficient Lifelong Learning with A-GEMcited by 1,058
  10. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 898
  11. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 763
  12. 2017Functional Map of the Worldcited by 338
27 more
  1. 2020Learning to Learn Single Domain Generalizationcited by 296
  2. 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
  3. 2021Gradient Matching for Domain Generalizationcited by 258
  4. 2021SelfReg: Self-supervised Contrastive Regularization for Domain Generalizationcited by 189
  5. 2021Fishr: Invariant Gradient Variances for Out-of-Distribution Generalizationcited by 186
  6. 2020Understanding Self-Training for Gradual Domain Adaptationcited by 149
  7. 2018Disentangled Sequential Autoencodercited by 120
  8. 2019Generalizing to unseen domains via distribution matchingcited by 110
  9. 2022The CLEAR Benchmark: Continual LEArning on Real-World Imagerycited by 93
  10. 2020Continuously Indexed Domain Adaptationcited by 75
  11. 2020Self-training Avoids Using Spurious Features Under Domain Shiftcited by 69
  12. 2015A Century of Portraits: A Visual Historical Record of American High School Yearbookscited by 54
  13. 2021Domain Invariant Representation Learning with Domain Density Transformationscited by 53
  14. 2021Feature Stylization and Domain-aware Contrastive Learning for Domain Generalizationcited by 40
  15. 2021KL Guided Domain Adaptationcited by 35
  16. 2022Temporal Domain Generalization with Drift-Aware Dynamic Neural Networkscited by 33
  17. 2018Some Theoretical Properties of GANscited by 27
  18. 2022Gradual Domain Adaptation without Indexed Intermediate Domainscited by 26
  19. 2023Fairness and Accuracy under Domain Generalizationcited by 24
  20. 2021Neuron Coverage-Guided Domain Generalizationcited by 19
  21. 2021Domain Generalization for Mammography Detection via Multi-style and Multi-view Contrastive Learningcited by 19
  22. 2022Generalizing to Evolving Domains with Latent Structure-Aware Sequential Autoencodercited by 19
  23. 2021On Learning Domain-Invariant Representations for Transfer Learning with Multiple Sourcescited by 15
  24. 2024Generalizing across Temporal Domains with Koopman Operatorscited by 13
  25. 2023Foresee What You Will Learn: Data Augmentation for Domain Generalization in Non-stationary Environmentcited by 11
  26. 2024Enhancing Evolving Domain Generalization through Dynamic Latent Representationscited by 6
  27. 2021Class-conditioned Domain Generalization via Wasserstein Distributional Robust Optimizationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 1.

4 papers.

  1. 2025Optimal Empirical Risk Minimization under Temporal Distribution Shiftscited by 2
  2. 2025FedDAA: Dynamic Client Clustering for Concept Drift Adaptation in Federated Learningcited by 1
  3. 2024Open-Set Heterogeneous Domain Adaptation: Theoretical Analysis and Algorithmcited by 0
  4. 2026From Relevance to Validity: Zero-Shot Tool Selection via Functional and Contextual Validationcited by 0