mlsanityData to 7 Oct 2026

Does enforcing fairness mitigate biases caused by subpopulation shift?

arXiv 2011.03173 ↗First posted 6 Nov 2020stat.ML cs.LGcited by 25

Not on the map. Why?

Abstract (arXiv)

Many instances of algorithmic bias are caused by subpopulation shifts. For example, ML models often perform worse on demographic groups that are underrepresented in the training data. In this paper, we study whether enforcing algorithmic fairness during training improves the performance of the trained model in the target domain. On one hand, we conceive scenarios in which enforcing fairness does not improve performance in the target domain. In fact, it may even harm performance. On the other hand, we derive necessary and sufficient conditions under which enforcing algorithmic fairness leads to the Bayes model in the target domain. We also illustrate the practical implications of our theoretical results in simulations and on real data.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 9; 2023: 7; 2024: 3; 2025: 3; 2026: 3.

25 papers.

Sort:

  1. 2022Improving the Fairness of Chest X-ray Classifierscited by 52
  2. 2023On the Independence of Association Bias and Empirical Fairness in Language Modelscited by 29
  3. 2022Subgroup Robustness Grows On Trees: An Empirical Baseline Investigationcited by 17
  4. 2023Improving Fair Training under Correlation Shiftscited by 14
  5. 2022Domain Adaptation meets Individual Fairness. And they get alongcited by 13
  6. 2022Certifying Some Distributional Fairness with Subpopulation Decompositioncited by 11
  7. 2022Input-agnostic Certified Group Fairness via Gaussian Parameter Smoothingcited by 11
  8. 2022Consistent Range Approximation for Fair Predictive Modelingcited by 7
  9. 2023Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Toolscited by 7
  10. 2022Metrizing Fairnesscited by 6
  11. 2023How Far Can Fairness Constraints Help Recover From Biased Data?cited by 5
  12. 2025Overcoming Fairness Trade-offs via Pre-processing: A Causal Perspectivecited by 5
13 more
  1. 2022Fairness in Forecasting of Observations of Linear Dynamical Systemscited by 4
  2. 2023f-FERM: A Scalable Framework for Robust Fair Empirical Risk Minimizationcited by 4
  3. 2023Domain Adaptive Decision Trees: Implications for Accuracy and Fairnesscited by 3
  4. 2024Is it Still Fair? A Comparative Evaluation of Fairness Algorithms through the Lens of Covariate Driftcited by 3
  5. 2022A Survey on Preserving Fairness Guarantees in Changing Environmentscited by 2
  6. 2024Microfoundation Inference for Strategic Predictioncited by 2
  7. 2025On Optimal Steering to Achieve Exact Fairnesscited by 2
  8. 2023On Comparing Fair Classifiers under Data Biascited by 1
  9. 2024A Note on Bias to Completecited by 1
  10. 2025Privilege Scorescited by 1
  11. 2026Fairness Under Group-Conditional Prior Probability Shift: Invariance, Drift, and Target-Aware Post-Processingcited by 1
  12. 2026Maximin Relative Improvement: Fair Learning as a Bargaining Problemcited by 0
  13. 2026Fix Representation (Optimally) Before Fairness: Finite-Sample Shrinkage Population Correction and the True Price of Fairness Under Subpopulation Shiftcited by 0