mlsanityData to 14 Oct 2026

Domain Adaptation meets Individual Fairness. And they get along

arXiv 2205.00504 ↗First posted 1 May 2022stat.ML cs.AI cs.CYcited by 13

Not on the map. Why?

Abstract (arXiv)

Many instances of algorithmic bias are caused by distributional shifts. For example, machine learning (ML) models often perform worse on demographic groups that are underrepresented in the training data. In this paper, we leverage this connection between algorithmic fairness and distribution shifts to show that algorithmic fairness interventions can help ML models overcome distribution shifts, and that domain adaptation methods (for overcoming distribution shifts) can mitigate algorithmic biases. In particular, we show that (i) enforcing suitable notions of individual fairness (IF) can improve the out-of-distribution accuracy of ML models under the covariate shift assumption and that (ii) it is possible to adapt representation alignment methods for domain adaptation to enforce individual fairness. The former is unexpected because IF interventions were not developed with distribution shifts in mind. The latter is also unexpected because representation alignment is not a common approach in the individual fairness literature.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 33 of its 56 references that are in the map. First posted on arXiv 1 May 2022.

Builds on

33 of 56 references.

References · 33

  1. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  2. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  3. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
  4. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
  5. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,247
  6. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
  7. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
  8. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 683
  9. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  10. 2015Return of Frustratingly Easy Domain Adaptationcited by 391
  11. 2019Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Settingcited by 349
  12. 2019Bridging Theory and Algorithm for Domain Adaptationcited by 332
21 more
  1. 2017Learning Generative Models with Sinkhorn Divergencescited by 314
  2. 2020Environment Inference for Invariant Learningcited by 306
  3. 2014Learning with Pseudo-Ensemblescited by 241
  4. 2018A DIRT-T Approach to Unsupervised Domain Adaptationcited by 215
  5. 2020BREEDS: Benchmarks for Subpopulation Shiftcited by 155
  6. 2017No Classification without Representation: Assessing Geodiversity Issues in Open Data Sets for the Developing Worldcited by 153
  7. 2018Counterfactual Fairness in Text Classification through Robustnesscited by 151
  8. 2019Training individually fair ML models with Sensitive Subspace Robustnesscited by 73
  9. 2018iFair: Learning Individually Fair Data Representations for Algorithmic Decision Makingcited by 64
  10. 2021Post-processing for Individual Fairnesscited by 61
  11. 2020Robust Fairness under Covariate Shiftcited by 58
  12. 2021DORO: Distributional and Outlier Robust Optimizationcited by 56
  13. 2020Two Simple Ways to Learn Individual Fairness Metrics from Datacited by 54
  14. 2019What's in a Name? Reducing Bias in Bios without Access to Protected Attributescited by 51
  15. 2021Optimal Representations for Covariate Shiftcited by 51
  16. 2019Recovering from Biased Data: Can Fairness Constraints Improve Accuracy?cited by 50
  17. 2020SenSeI: Sensitive Set Invariance for Enforcing Individual Fairnesscited by 37
  18. 2019Transfer of Machine Learning Fairness across Domainscited by 36
  19. 2020Does enforcing fairness mitigate biases caused by subpopulation shift?cited by 25
  20. 2019Debiasing Embeddings for Reduced Gender Bias in Text Classificationcited by 19
  21. 2020On Localized Discrepancy for Domain Adaptationcited by 14

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 7; 2024: 4; 2025: 1.

13 papers.

Sort:

  1. 2024FairDomain: Achieving Fairness in Cross-Domain Medical Image Segmentation and Classificationcited by 19
  2. 2023Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approachcited by 12
  3. 2023Fairness in Visual Clustering: A Novel Transformer Clustering Approachcited by 10
  4. 2023Are demographically invariant models and representations in medical imaging fair?cited by 6
  5. 2023Retiring DeltaDP: New Distribution-Level Metrics for Demographic Paritycited by 4
  6. 2023Domain Adaptive Decision Trees: Implications for Accuracy and Fairnesscited by 3
  7. 2022A Survey on Preserving Fairness Guarantees in Changing Environmentscited by 2
  8. 2023Adapting Machine Learning Diagnostic Models to New Populations Using a Small Amount of Data: Results from Clinical Neurosciencecited by 2
  9. 2023Certification of Distributional Individual Fairnesscited by 2
  10. 2024A Note on Bias to Completecited by 1
  11. 2024A Comprehensive Review of Machine Learning Advances on Data Change: A Cross-Field Perspectivecited by 1
  12. 2024Revisiting Technical Bias Mitigation Strategiescited by 0
1 more
  1. 2025Position: Beyond Sensitive Attributes, ML Fairness Should Quantify Structural Injustice via Social Determinantscited by 0