mlsanityData to 7 Oct 2026

Learning Controllable Fair Representations

arXiv 1812.04218 ↗First posted 11 Dec 2018cs.LG cs.AI stat.MLcited by 83

Not on the map. Why?

Abstract (arXiv)

Learning data representations that are transferable and are fair with respect to certain protected attributes is crucial to reducing unfair decisions while preserving the utility of the data. We propose an information-theoretically motivated objective for learning maximally expressive representations subject to fairness constraints. We demonstrate that a range of existing approaches optimize approximations to the Lagrangian dual of our objective. In contrast to these existing approaches, our objective allows the user to control the fairness of the representations by specifying limits on unfairness. Exploiting duality, we introduce a method that optimizes the model parameters as well as the expressiveness-fairness trade-off. Empirical evidence suggests that our proposed method can balance the trade-off between multiple notions of fairness and achieves higher expressiveness at a lower computational cost.

Key facts. Cited by 83 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 33; 2023: 17; 2024: 10; 2025: 4; 2026: 1.

83 papers.

Sort:

By area:

  1. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  2. 2021D2C: Diffusion-Denoising Models for Few-shot Conditional Generationcited by 96
  3. 2021FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoderscited by 75
  4. 2022Fair Contrastive Learning for Facial Attribute Classificationcited by 71
  5. 2022Improving the Fairness of Chest X-ray Classifierscited by 52
  6. 2022Fair and Optimal Classification via Post-Processingcited by 50
  7. 2021Controllable Guarantees for Fair Outcomes via Contrastive Information Estimationcited by 45
  8. 2021Fair Normalizing Flowscited by 38
  9. 2022On Learning Fairness and Accuracy on Multiple Subgroupscited by 31
  10. 2022Understanding Instance-Level Impact of Fairness Constraintscited by 27
  11. 2021Conditional Contrastive Learning for Improving Fairness in Self-Supervised Learningcited by 25
  12. 2024Training Unbiased Diffusion Models From Biased Datasetcited by 25
38 more
  1. 2023Efficient fair PCA for fair representation learningcited by 23
  2. 2022Fair Representation Learning through Implicit Path Alignmentcited by 22
  3. 2022Transferring Fairness under Distribution Shifts via Fair Consistency Regularizationcited by 21
  4. 2022FARE: Provably Fair Representation Learning with Practical Certificatescited by 21
  5. 2022Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairnesscited by 21
  6. 2023From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modelingcited by 21
  7. 2021Tight Mutual Information Estimation With Contrastive Fenchel-Legendre Optimizationcited by 18
  8. 2021Latent Space Smoothing for Individually Fair Representationscited by 18
  9. 2022What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspectivecited by 18
  10. 2022On the Versatile Uses of Partial Distance Correlation in Deep Learningcited by 18
  11. 2023FLAC: Fairness-Aware Representation Learning by Suppressing Attribute-Class Associationscited by 18
  12. 2021Explaining Algorithmic Fairness Through Fairness-Aware Causal Path Decompositioncited by 17
  13. 2021Fair Representation: Guaranteeing Approximate Multiple Group Fairness for Unknown Taskscited by 16
  14. 2022Net benefit, calibration, threshold selection, and training objectives for algorithmic fairness in healthcarecited by 16
  15. 2022Controlling Directions Orthogonal to a Classifiercited by 13
  16. 2022A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairnesscited by 13
  17. 2021On Characterizing the Trade-off in Invariant Representation Learningcited by 12
  18. 2022Don't Throw it Away! The Utility of Unlabeled Data in Fair Decision Makingcited by 12
  19. 2022Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utilitycited by 12
  20. 2022Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learningcited by 11
  21. 2022You Don't Know My Favorite Color: Preventing Dialogue Representations from Revealing Speakers' Private Personascited by 11
  22. 2022Certifying Some Distributional Fairness with Subpopulation Decompositioncited by 11
  23. 2022Input-agnostic Certified Group Fairness via Gaussian Parameter Smoothingcited by 11
  24. 2021Impossibility results for fair representationscited by 10
  25. 2021Attributing Fair Decisions with Attention Interventionscited by 10
  26. 2022Attainability and Optimality: The Equalized Odds Fairness Revisitedcited by 10
  27. 2022Fairness-aware Model-agnostic Positive and Unlabeled Learningcited by 10
  28. 2023Robust Concept Erasure via Kernelized Rate-Distortion Maximizationcited by 10
  29. 2021Robust Fairness-aware Learning Under Sample Selection Biascited by 9
  30. 2024Fair Bilevel Neural Network (FairBiNN): On Balancing fairness and accuracy via Stackelberg Equilibriumcited by 9
  31. 2025Prediction-Powered Causal Inferencescited by 9
  32. 2021AI Fairness via Domain Adaptationcited by 8
  33. 2023Scalable Infomin Learningcited by 8
  34. 2021Fair Representations by Compressioncited by 7
  35. 2022Disentangled Representation with Causal Constraints for Counterfactual Fairnesscited by 7
  36. 2025Fair Representation Learning for Continuous Sensitive Attributes using Expectation of Integral Probability Metricscited by 7
  37. 2022Ultra-marginal Feature Importance: Learning from Data with Causal Guaranteescited by 6
  38. 2023DualFair: Fair Representation Learning at Both Group and Individual Levels via Contrastive Self-supervisioncited by 6

50 most cited of 83 All 83 (JSON)