mlsanityData to 7 Oct 2026

Causal Balancing for Domain Generalization

arXiv 2206.05263 ↗First posted 10 Jun 2022cs.LG cs.AI cs.CVcited by 20

Not on the map. Why?

Abstract (arXiv)

While machine learning models rapidly advance the state-of-the-art on various real-world tasks, out-of-domain (OOD) generalization remains a challenging problem given the vulnerability of these models to spurious correlations. We propose a balanced mini-batch sampling strategy to transform a biased data distribution into a spurious-free balanced distribution, based on the invariance of the underlying causal mechanisms for the data generation process. We argue that the Bayes optimal classifiers trained on such balanced distribution are minimax optimal across a diverse enough environment space. We also provide an identifiability guarantee of the latent variable model of the proposed data generation process, when utilizing enough train environments. Experiments are conducted on DomainBed, demonstrating empirically that our method obtains the best performance across 20 baselines reported on the benchmark.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 56 of its 79 references that are in the map. First posted on arXiv 10 Jun 2022.

Builds on

56 of 79 references.

References · 56

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2013Auto-Encoding Variational Bayescited by 3,980
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  6. 2019Invariant Risk Minimizationcited by 1,832
  7. 2016Variational Inference: A Review for Statisticianscited by 1,466
  8. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  9. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  10. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  11. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  12. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
38 more
  1. 2020In Search of Lost Domain Generalizationcited by 1,042
  2. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  3. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
  4. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  5. 2018Recognition in Terra Incognitacited by 655
  6. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 533
  7. 2021Just Train Twice: Improving Group Robustness without Training Group Informationcited by 522
  8. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 494
  9. 2020Self-Challenging Improves Cross-Domain Generalizationcited by 426
  10. 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 322
  11. 2020The Risks of Invariant Risk Minimizationcited by 262
  12. 2021Gradient Matching for Domain Generalizationcited by 258
  13. 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
  14. 2019Adversarial Domain Adaptation with Domain Mixupcited by 250
  15. 2020Domain Generalization using Causal Matchingcited by 224
  16. 2021Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalizationcited by 220
  17. 2021D'ya like DAGs? A Survey on Structure Learning and Causal Discoverycited by 209
  18. 2021SelfReg: Self-supervised Contrastive Regularization for Domain Generalizationcited by 189
  19. 2021Fishr: Invariant Gradient Variances for Out-of-Distribution Generalizationcited by 186
  20. 2020Adaptive Risk Minimization: Learning to Adapt to Domain Shiftcited by 183
  21. 2017Domain Generalization by Marginal Transfer Learningcited by 180
  22. 2021On Calibration and Out-of-domain Generalizationcited by 134
  23. 2020Learning explanations that are hard to varycited by 132
  24. 2021Does Invariant Risk Minimization Capture Invariance?cited by 116
  25. 2017Measuring the tendency of CNNs to Learn Surface Statistical Regularitiescited by 87
  26. 2021Invariant Information Bottleneck for Domain Generalizationcited by 86
  27. 2020Learning from others' mistakes: Avoiding dataset biases without modeling themcited by 83
  28. 2020A causal framework for distribution generalizationcited by 68
  29. 2021Examining and Combating Spurious Features under Distribution Shiftcited by 64
  30. 2020Learning Causal Semantic Representation for Out-of-Distribution Predictioncited by 60
  31. 2018Perfect Match: A Simple Method for Learning Representations For Counterfactual Inference With Neural Networkscited by 55
  32. 2021Causally motivated Shortcut Removal Using Auxiliary Labelscited by 55
  33. 2021SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalizationcited by 50
  34. 2013Density Estimation in Infinite Dimensional Exponential Familiescited by 41
  35. 2020Diagnosing the Environment Bias in Vision-and-Language Navigationcited by 41
  36. 2021Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlationscited by 41
  37. 2021A Style and Semantic Memory Mechanism for Domain Generalizationcited by 32
  38. 2017Estimation of causal effects with multiple treatments: a review and new ideascited by 29

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 9; 2025: 5; 2026: 3.

20 papers.

Sort:

By area:

  1. 2023Flatness-Aware Minimization for Domain Generalizationcited by 27
  2. 2025A Causal Adjustment Module for Debiasing Scene Graph Generationcited by 14
  3. 2023Causal reasoning in typical computer vision taskscited by 12
  4. 2024Rethinking Misalignment in Vision-Language Model Adaptation from a Causal Perspectivecited by 9
  5. 2024HCVP: Leveraging Hierarchical Contrastive Visual Prompt for Domain Generalizationcited by 8
  6. 2024Learning Generalizable Models via Disentangling Spurious and Enhancing Potential Correlationscited by 5
  7. 2024Towards Identifiable Latent Additive Noise Modelscited by 5
  8. 2024Scalable Out-of-distribution Robustness in the Presence of Unobserved Confounderscited by 5
  9. 2025Gradient Extrapolation for Debiased Representation Learningcited by 4
  10. 2024How Does Distribution Matching Help Domain Generalization: An Information-theoretic Analysiscited by 3
  11. 2025Superclass-Guided Representation Disentanglement for Spurious Correlation Mitigationcited by 2
  12. 2024Revisiting Spurious Correlation in Domain Generalizationcited by 1
8 more
  1. 2024DICS: Find Domain-Invariant and Class-Specific Features for Out-of-Distribution Generalizationcited by 1
  2. 2025Subgroups Matter for Robust Bias Mitigationcited by 1
  3. 2025A Reverse Causal Framework to Mitigate Spurious Correlations for Debiasing Scene Graph Generationcited by 1
  4. 2022Direct-Effect Risk Minimization for Domain Generalizationcited by 0
  5. 2024Invariant Correlation of Representation with Label: Enhancing Domain Generalization in Noisy Environmentscited by 0
  6. 2026A Causal Framework for Mitigating Data Shifts in Healthcarecited by 0
  7. 2026How Many Samples Are Enough for Learning Across Domains?cited by 0
  8. 2026Can Domain Generalization be Guaranteed in Small-Sample Learning?cited by 0