mlsanityData to 7 Oct 2026

Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraints

arXiv 1807.00028 ↗First posted 29 Jun 2018cs.LG stat.MLcited by 53

Not on the map. Why?

Abstract (arXiv)

Classifiers can be trained with data-dependent constraints to satisfy fairness goals, reduce churn, achieve a targeted false positive rate, or other policy goals. We study the generalization performance for such constrained optimization problems, in terms of how well the constraints are satisfied at evaluation time, given that they are satisfied at training time. To improve generalization performance, we frame the problem as a two-player game where one player optimizes the model parameters on a training dataset, and the other player enforces the constraints on an independent validation dataset. We build on recent work in two-player constrained optimization to show that if one uses this two-dataset approach, then constraint generalization can be significantly improved. As we illustrate experimentally, this approach works not only in theory, but also in practice.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 9; 2023: 15; 2024: 4; 2025: 5; 2026: 6.

53 papers.

Sort:

By area:

  1. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  2. 2021Fair Mixup: Fairness via Interpolationcited by 109
  3. 2021Constrained Learning with Non-Convex Lossescited by 42
  4. 2021Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task Learningcited by 34
  5. 2021An Empirical Framework for Domain Generalization in Clinical Settingscited by 32
  6. 2021Evaluating Debiasing Techniques for Intersectional Biasescited by 30
  7. 2022Escaping Saddle Points for Effective Generalization on Class-Imbalanced Datacited by 28
  8. 2021Measuring Generalization with Optimal Transportcited by 24
  9. 2021A Sociotechnical View of Algorithmic Fairnesscited by 24
  10. 2021Fast Approximations for Job Shop Scheduling: A Lagrangian Dual Deep Learning Methodcited by 20
  11. 2022What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspectivecited by 18
  12. 2022Net benefit, calibration, threshold selection, and training objectives for algorithmic fairness in healthcarecited by 16
38 more
  1. 2022Active Learning with Safety Constraintscited by 16
  2. 2022Instance-optimal PAC Algorithms for Contextual Banditscited by 16
  3. 2022FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Datacited by 13
  4. 2023FAIRER: Fairness as Decision Rationale Alignmentcited by 12
  5. 2021Training Over-parameterized Models with Non-decomposable Objectivescited by 11
  6. 2023Cross-Institutional Transfer Learning for Educational Models: Implications for Model Performance, Fairness, and Equitycited by 9
  7. 2024Near-Optimal Solutions of Constrained Learning Problemscited by 9
  8. 2024Fair Bilevel Neural Network (FairBiNN): On Balancing fairness and accuracy via Stackelberg Equilibriumcited by 9
  9. 2021Fairness Through Regularization for Learning to Rankcited by 8
  10. 2021Task-Adaptive Neural Network Search with Meta-Contrastive Learningcited by 8
  11. 2023Data Augmentation via Subgroup Mixup for Improving Fairnesscited by 8
  12. 2023Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Toolscited by 7
  13. 2024Secure and Confidential Certificates of Online Fairnesscited by 7
  14. 2022Estimating and Controlling for Equalized Odds via Sensitive Attribute Predictorscited by 5
  15. 2023fairml: A Statistician's Take on Fair Machine Learning Modellingcited by 4
  16. 2023A Theoretical Approach to Characterize the Accuracy-Fairness Trade-off Pareto Frontiercited by 4
  17. 2025Position: Adopt Constraints Over Fixed Penalties in Deep Learningcited by 4
  18. 2021Fairness-aware Summarization for Justified Decision-Makingcited by 3
  19. 2021A Pre-processing Method for Fairness in Rankingcited by 3
  20. 2023Fair-CDA: Continuous and Directional Augmentation for Group Fairnesscited by 3
  21. 2022Distraction is All You Need for Fairnesscited by 2
  22. 2023MLHOps: Machine Learning for Healthcare Operationscited by 2
  23. 2023Towards Bridging the FL Performance-Explainability Trade-Off: A Trustworthy 6G RAN Slicing Use-Casecited by 2
  24. 2023Fair Few-shot Learning with Auxiliary Setscited by 2
  25. 2023Fair Active Learning in Low-Data Regimescited by 2
  26. 2024Specification Overfitting in Artificial Intelligencecited by 2
  27. 2025Exact Reformulation and Optimization for Direct Metric Optimization in Binary Imbalanced Classificationcited by 2
  28. 2025A Dual Perspective on Decision-Focused Learning: Scalable Training via Dual-Guided Surrogatescited by 2
  29. 2023Towards clinical AI fairness: A translational perspectivecited by 1
  30. 2023Explanation-Guided Fair Federated Learning for Transparent 6G RAN Slicingcited by 1
  31. 2025Fair-FLIP: Fair Deepfake Detection with Fairness-Oriented Final Layer Input Prioritisingcited by 1
  32. 2026Fairness Aware Reward Optimizationcited by 1
  33. 2021The Price of Diversitycited by 0
  34. 2023Calibrated Data-Dependent Constraints with Exact Satisfaction Guaranteescited by 0
  35. 2023GroupMixNorm Layer for Learning Fair Modelscited by 0
  36. 2025Private Rate-Constrained Optimization with Applications to Fair Learningcited by 0
  37. 2026Separation-Utility Pareto Frontier: An Information-Theoretic Characterizationcited by 0
  38. 2026Residual-Controlled Multiplier Learning for Stochastic Constrained Decision-Makingcited by 0

50 most cited of 53 All 53 (JSON)