mlsanityData to 7 Oct 2026

Understanding and Mitigating Accuracy Disparity in Regression

arXiv 2102.12013 ↗First posted 24 Feb 2021cs.LG cs.CY stat.MLcited by 17

Not on the map. Why?

Abstract (arXiv)

With the widespread deployment of large-scale prediction systems in high-stakes domains, e.g., face recognition, criminal justice, etc., disparity in prediction accuracy between different demographic subgroups has called for fundamental understanding on the source of such disparity and algorithmic intervention to mitigate it. In this paper, we study the accuracy disparity problem in regression. To begin with, we first propose an error decomposition theorem, which decomposes the accuracy disparity into the distance between marginal label distributions and the distance between conditional representations, to help explain why such accuracy disparity appears in practice. Motivated by this error decomposition and the general idea of distribution alignment with statistical distances, we then propose an algorithm to reduce this disparity, and analyze its game-theoretic optima of the proposed objective functions. To corroborate our theoretical findings, we also conduct experiments on five benchmark datasets. The experimental results suggest that our proposed algorithms can effectively mitigate accuracy disparity while maintaining the predictive power of the regression models.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 29 of its 58 references that are in the map. First posted on arXiv 24 Feb 2021.

Builds on

29 of 58 references.

References · 29

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  3. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  4. 2014Certifying and removing disparate impactcited by 715
  5. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  6. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 368
  7. 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 363
  8. 2018Learning Adversarially Fair and Transferable Representationscited by 353
  9. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
  10. 2017Fairness in Criminal Justice Risk Assessments: The State of the Artcited by 315
  11. 2015The Variational Fair Autoencodercited by 223
  12. 2015Censoring Representations with an Adversarycited by 191
17 more
  1. 2019Fair Regression: Quantitative Definitions and Reduction-based Algorithmscited by 168
  2. 2017Data Decisions and Theoretical Implications when Adversarially Learning Fair Representationscited by 165
  3. 2019Inherent Tradeoffs in Learning Fair Representationscited by 144
  4. 2018Why Is My Classifier Discriminatory?cited by 143
  5. 2020Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification Taskscited by 137
  6. 2019Wasserstein Fair Classificationcited by 131
  7. 2020Fair Regression with Wasserstein Barycenterscited by 99
  8. 2018The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimizationcited by 98
  9. 2020Classification vs regression in overparameterized regimes: Does the loss function matter?cited by 97
  10. 2019Conditional Learning of Fair Representationscited by 78
  11. 2019Pairwise Fairness for Ranking and Regressioncited by 58
  12. 2020Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionatelycited by 52
  13. 2018Fairness Through Causal Awareness: Learning Latent-Variable Models for Biased Datacited by 39
  14. 2020Fundamental Limits and Tradeoffs in Invariant Representation Learningcited by 38
  15. 2019Fair Regression for Health Care Spendingcited by 10
  16. 2020An implicit function learning approach for parametric modal regressioncited by 7
  17. 2019Feature Noise Induces Loss Discrepancy Across Groupscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 3; 2023: 4; 2024: 3; 2025: 2; 2026: 2.

17 papers.

Sort:

  1. 2021Selective Regression Under Fairness Criteriacited by 34
  2. 2022Subgroup Robustness Grows On Trees: An Empirical Baseline Investigationcited by 17
  3. 2023Equal Opportunity of Coverage in Fair Regressioncited by 16
  4. 2021Towards Return Parity in Markov Decision Processescited by 12
  5. 2022Understanding the Impact of Adversarial Robustness on Accuracy Disparitycited by 9
  6. 2021Costs and Benefits of Fair Regressioncited by 8
  7. 2023Mean Parity Fair Regression in RKHScited by 6
  8. 2023Adapting Static Fairness to Sequential Decision-Making: Bias Mitigation Strategies towards Equal Long-term Benefit Ratecited by 6
  9. 2024Differentially Private Post-Processing for Fair Regressioncited by 5
  10. 2022Fairness-aware Regression Robust to Adversarial Attackscited by 4
  11. 2023Challenges and Opportunities in Improving Worst-Group Generalization in Presence of Spurious Featurescited by 4
  12. 2024Pursuing Overall Welfare in Federated Learning through Sequential Decision Makingcited by 2
5 more
  1. 2025Intersectional Divergence: Measuring Fairness in Regressioncited by 1
  2. 2026RPWithPrior: Label Differential Privacy in Regressioncited by 1
  3. 2024Alpha and Prejudice: Improving α-sized Worst-case Fairness via Intrinsic Reweightingcited by 0
  4. 2025Wasserstein projection distance for fairness testing of regression modelscited by 0
  5. 2026StackingNet: Collective Inference Across Independent AI Foundation Modelscited by 0