mlsanityData to 7 Oct 2026

Support and Invertibility in Domain-Invariant Representations

arXiv 1903.03448 ↗First posted 8 Mar 2019stat.ML cs.LGcited by 87

Not on the map. Why?

Abstract (arXiv)

Learning domain-invariant representations has become a popular approach to unsupervised domain adaptation and is often justified by invoking a particular suite of theoretical results. We argue that there are two significant flaws in such arguments. First, the results in question hold only for a fixed representation and do not account for information lost in non-invertible transformations. Second, domain invariance is often a far too strict requirement and does not always lead to consistent estimation, even under strong and favorable assumptions. In this work, we give generalization bounds for unsupervised domain adaptation that hold for any representation function by acknowledging the cost of non-invertibility. In addition, we show that penalizing distance between densities is often wasteful and propose a bound based on measuring the extent to which the support of the source domain covers the target domain. We perform experiments on well-known benchmarks that illustrate the short-comings of current standard practice.

Key facts. Cited by 87 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 31; 2022: 18; 2023: 18; 2024: 6; 2025: 9; 2026: 5.

87 papers.

Sort:

By area:

  1. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  2. 2021Fishr: Invariant Gradient Variances for Out-of-Distribution Generalizationcited by 186
  3. 2021A Fine-Grained Analysis on Distribution Shiftcited by 171
  4. 2021Self-supervised Augmentation Consistency for Adapting Semantic Segmentationcited by 149
  5. 2021Nonparametric Estimation of Heterogeneous Treatment Effects: From Theory to Learning Algorithmscited by 144
  6. 2021Cycle Self-Training for Domain Adaptationcited by 120
  7. 2021Towards a Theoretical Framework of Out-of-Distribution Generalizationcited by 94
  8. 2021Invariant Information Bottleneck for Domain Generalizationcited by 86
  9. 2021Exploiting Domain-Specific Features to Enhance Domain Generalizationcited by 86
  10. 2021Desiderata for Representation Learning: A Causal Perspectivecited by 76
  11. 2021A Prototype-Oriented Framework for Unsupervised Domain Adaptationcited by 62
  12. 2022Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equationscited by 59
38 more
  1. 2021Causally motivated Shortcut Removal Using Auxiliary Labelscited by 55
  2. 2021Optimal Representations for Covariate Shiftcited by 51
  3. 2021Domain Adversarial Neural Networks for Domain Generalization: When It Works and How to Improvecited by 46
  4. 2021KL Guided Domain Adaptationcited by 35
  5. 2022Modeling the Data-Generating Process is Necessary for Out-of-Distribution Generalizationcited by 34
  6. 2022Domain-invariant Feature Exploration for Domain Generalizationcited by 34
  7. 2023RLSbench: Domain Adaptation Under Relaxed Label Shiftcited by 30
  8. 2021An Information-theoretic Approach to Distribution Shiftscited by 25
  9. 2021SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Datacited by 25
  10. 2021Aggregating From Multiple Target-Shifted Sourcescited by 24
  11. 2023Out-of-Domain Robustness via Targeted Augmentationscited by 24
  12. 2021ADAST: Attentive Cross-domain EEG-based Sleep Staging Framework with Iterative Self-Trainingcited by 17
  13. 2021On Learning Domain-Invariant Representations for Transfer Learning with Multiple Sourcescited by 15
  14. 2021Limitations of Post-Hoc Feature Alignment for Robustnesscited by 14
  15. 2022A Contrastive Objective for Learning Disentangled Representationscited by 14
  16. 2023Causal Effect Estimation: Recent Advances, Challenges, and Opportunitiescited by 14
  17. 2022Deep Multi-Modal Structural Equations For Causal Effect Estimation With Unstructured Proxiescited by 13
  18. 2022PAC-Bayesian Domain Adaptation Bounds for Multiclass Learnerscited by 13
  19. 2022The Change that Matters in Discourse Parsing: Estimating the Impact of Domain Shift on Parser Errorcited by 12
  20. 2022Adapting to Latent Subgroup Shifts via Concepts and Proxiescited by 12
  21. 2023Make the U in UDA Matter: Invariant Consistency Learning for Unsupervised Domain Adaptationcited by 12
  22. 2021Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoningcited by 11
  23. 2021Partial Domain Adaptation without Domain Alignmentcited by 11
  24. 2022Class Prior Estimation under Covariate Shift: No Problem?cited by 10
  25. 2025Does Unsupervised Domain Adaptation Improve the Robustness of Amortized Bayesian Inference? A Systematic Evaluationcited by 10
  26. 2021β-Intact-VAE: Identifying and Estimating Causal Effects under Limited Overlapcited by 8
  27. 2023Are demographically invariant models and representations in medical imaging fair?cited by 6
  28. 2025Domain Adaptation and Entanglement: an Optimal Transport Perspectivecited by 6
  29. 2025SIMSHIFT: A Benchmark for Adapting Neural Surrogates to Distribution Shiftscited by 6
  30. 2022Adversarial Support Alignmentcited by 5
  31. 2023Sparse joint shift in multinomial classificationcited by 5
  32. 2023Prominent Roles of Conditionally Invariant Components in Domain Adaptation: Theory and Algorithmscited by 5
  33. 2025When Shift Happens - Confounding Is to Blamecited by 5
  34. 2022On Certifying and Improving Generalization to Unseen Domainscited by 4
  35. 2022Factorizable Joint Shift in Multinomial Classificationcited by 4
  36. 2022LEATHER: A Framework for Learning to Generate Human-like Text in Dialoguecited by 4
  37. 2023INSURE: An Information Theory Inspired Disentanglement and Purification Model for Domain Generalizationcited by 4
  38. 2024Deep Transfer Learning: Model Framework and Error Analysiscited by 4

50 most cited of 87 All 87 (JSON)