mlsanityData to 7 Oct 2026

On Learning Fairness and Accuracy on Multiple Subgroups

arXiv 2210.10837 ↗First posted 19 Oct 2022stat.ML cs.CY cs.LGcited by 31

Not on the map. Why?

Abstract (arXiv)

We propose an analysis in fair learning that preserves the utility of the data while reducing prediction disparities under the criteria of group sufficiency. We focus on the scenario where the data contains multiple or even many subgroups, each with limited number of samples. As a result, we present a principled method for learning a fair predictor for all subgroups via formulating it as a bilevel objective. Specifically, the subgroup specific predictors are learned in the lower-level through a small amount of data and the fair predictor. In the upper-level, the fair predictor is updated to be close to all subgroup specific predictors. We further prove that such a bilevel objective can effectively control the group sufficiency and generalization error. We evaluate the proposed framework on real-world datasets. Empirical evidence suggests the consistently improved fair predictions, as well as the comparable accuracy to the baselines.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Builds on 42 of its 71 references that are in the map. First posted on arXiv 19 Oct 2022.

Builds on

42 of 71 references.

References · 42

  1. 2017On Calibration of Modern Neural Networkscited by 4,860
  2. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  3. 2013Auto-Encoding Variational Bayescited by 3,980
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  5. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  6. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  7. 2015Automatic differentiation in machine learning: a surveycited by 846
  8. 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 671
  9. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
  10. 2017On Fairness and Calibrationcited by 406
  11. 2019Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classificationcited by 396
  12. 2019Fair Resource Allocation in Federated Learningcited by 389
30 more
  1. 2017Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairnesscited by 381
  2. 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 363
  3. 2018Learning Adversarially Fair and Transferable Representationscited by 353
  4. 2020Environment Inference for Invariant Learningcited by 306
  5. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
  6. 2018Empirical Risk Minimization under Fairness Constraintscited by 226
  7. 2021Societal Biases in Language Generation: Progress and Challengescited by 201
  8. 2019Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practicescited by 170
  9. 2021Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyondcited by 151
  10. 2019Wasserstein Fair Classificationcited by 131
  11. 2021Fair Mixup: Fairness via Interpolationcited by 109
  12. 2021Understanding and Evaluating Racial Biases in Image Captioningcited by 108
  13. 2018Learning Controllable Fair Representationscited by 83
  14. 2019Conditional Learning of Fair Representationscited by 78
  15. 2017Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theorycited by 76
  16. 2019Meta-Curvaturecited by 70
  17. 2013A PAC-Bayesian bound for Lifelong Learningcited by 69
  18. 2021Fair Feature Distillation for Visual Recognitioncited by 59
  19. 2022FairLex: A Multilingual Benchmark for Evaluating Fairness in Legal Text Processingcited by 48
  20. 2021Discover the Unknown Biased Attribute of an Image Classifiercited by 46
  21. 2021Generalization Bounds For Meta-Learning: An Information-Theoretic Analysiscited by 45
  22. 2022Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversalcited by 40
  23. 2021Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task Learningcited by 34
  24. 2021First the worst: Finding better gender translations during beam searchcited by 28
  25. 2019Stable and Fair Classificationcited by 25
  26. 2019Towards Understanding Gender Bias in Relation Extractioncited by 23
  27. 2022Fair Representation Learning through Implicit Path Alignmentcited by 22
  28. 2021Fairness-aware Class Imbalanced Learningcited by 19
  29. 2019Fairness With Minimal Harm: A Pareto-Optimal Approach For Healthcarecited by 16
  30. 2019What is Fair? Exploring Pareto-Efficiency for Fairness Constrained Classifierscited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 10; 2024: 10; 2025: 6; 2026: 4.

31 papers.

Sort:

  1. 2023When Source-Free Domain Adaptation Meets Learning with Noisy Labelscited by 46
  2. 2023A Survey on Intersectional Fairness in Machine Learning: Notions, Mitigation, and Challengescited by 41
  3. 2023FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methodscited by 33
  4. 2022Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalizationcited by 22
  5. 2023On Fairness of Medical Image Classification with Multiple Sensitive Attributes via Learning Orthogonal Representationscited by 17
  6. 2023Multi-dimensional discrimination in Law and Machine Learning -- A comparative overviewcited by 15
  7. 2024A Short Survey on Importance Weighting for Machine Learningcited by 15
  8. 2024Fairness Without Harm: An Influence-Guided Active Sampling Approachcited by 12
  9. 2023Understanding Fairness Surrogate Functions in Algorithmic Fairnesscited by 8
  10. 2023Algorithm-Dependent Bounds for Representation Learning of Multi-Source Domain Adaptationcited by 7
  11. 2023Balancing Act: Constraining Disparate Impact in Sparse Modelscited by 7
  12. 2024Towards Standardizing AI Bias Explorationcited by 5
19 more
  1. 2024Intersectional Unfairness Discoverycited by 5
  2. 2024Fairness-Aware Estimation of Graphical Modelscited by 5
  3. 2023A Theoretical Approach to Characterize the Accuracy-Fairness Trade-off Pareto Frontiercited by 4
  4. 2023f-FERM: A Scalable Framework for Robust Fair Empirical Risk Minimizationcited by 4
  5. 2024Fairness without Demographics through Learning Graph of Gradientscited by 4
  6. 2024On the Maximal Local Disparity of Fairness-Aware Classifierscited by 3
  7. 2025Fairness Overfitting in Machine Learning: An Information-Theoretic Perspectivecited by 3
  8. 2026Full spectrum Unlearnable Examples via Spectral Equalizationcited by 3
  9. 2024FairLoRA: Unpacking Bias Mitigation in Vision Models with Fairness-Driven Low-Rank Adaptationcited by 2
  10. 2025M2FGB: A Min-Max Gradient Boosting Framework for Subgroup Fairnesscited by 1
  11. 2025Fair CCA for Fair Representation Learning: An ADNI Studycited by 1
  12. 2025Doubly-Regressing Approach for Subgroup Fairnesscited by 1
  13. 2024Practical Guide for Causal Pathways and Sub-group Disparity Analysiscited by 0
  14. 2024MABR: Multilayer Adversarial Bias Removal Without Prior Bias Knowledgecited by 0
  15. 2025A Critical Review of Predominant Bias in Neural Networkscited by 0
  16. 2025Component-Based Fairness in Face Attribute Classification with Bayesian Network-informed Meta Learningcited by 0
  17. 2026Federated Learning at the Forefront of Fairness: A Multifaceted Perspectivecited by 0
  18. 2026Differential Subgroup Discovery: Characterizing Where Two Populations Differ, and Whycited by 0
  19. 2026Fair Dataset Distillation via Cross-Group Barycenter Alignmentcited by 0