mlsanityData to 7 Oct 2026

Flexibly Fair Representation Learning by Disentanglement

arXiv 1906.02589 ↗First posted 6 Jun 2019cs.LG cs.AI stat.MLcited by 196

Not on the map. Why?

Abstract (arXiv)

We consider the problem of learning representations that achieve group and subgroup fairness with respect to multiple sensitive attributes. Taking inspiration from the disentangled representation learning literature, we propose an algorithm for learning compact representations of datasets that are useful for reconstruction and prediction, but are also flexibly fair, meaning they can be easily modified at test time to achieve subgroup demographic parity with respect to multiple sensitive attributes and their conjunctions. We show empirically that the resulting encoder---which does not require the sensitive attributes for inference---enables the adaptation of a single representation to a variety of fair classification tasks with new target labels and subgroup definitions.

Key facts. Cited by 196 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 41; 2022: 56; 2023: 37; 2024: 30; 2025: 20; 2026: 12.

196 papers.

Sort:

By area:

  1. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  2. 2022Fair Contrastive Learning for Facial Attribute Classificationcited by 71
  3. 2022MEDFAIR: Benchmarking Fairness for Medical Imagingcited by 66
  4. 2021Fair Feature Distillation for Visual Recognitioncited by 59
  5. 2022Discover and Mitigate Unknown Biases with Debiasing Alternate Networkscited by 47
  6. 2021Discover the Unknown Biased Attribute of an Image Classifiercited by 46
  7. 2021Learning Disentangled Representations in the Imaging Domaincited by 46
  8. 2021Towards Fair Classifiers Without Sensitive Attributes: Exploring Biases in Related Featurescited by 45
  9. 2021Learning Fair Classifiers with Partially Annotated Group Labelscited by 40
  10. 2023Disentanglement via Latent Quantizationcited by 40
  11. 2021Fair Normalizing Flowscited by 38
  12. 2022FMP: Toward Fair Graph Message Passing against Topology Biascited by 35
38 more
  1. 2021Learning Bias-Invariant Representation by Cross-Sample Mutual Information Minimizationcited by 32
  2. 2022Learning Fair Representation via Distributional Contrastive Disentanglementcited by 31
  3. 2022Invariant Causal Mechanisms through Distribution Matchingcited by 31
  4. 2021An Image is Worth More Than a Thousand Words: Towards Disentanglement in the Wildcited by 30
  5. 2021Where and What? Examining Interpretable Disentangled Representationscited by 27
  6. 2022Addressing Fairness Issues in Deep Learning-Based Medical Image Analysis: A Systematic Reviewcited by 27
  7. 2023Survey of Social Bias in Vision-Language Modelscited by 26
  8. 2021Conditional Contrastive Learning for Improving Fairness in Self-Supervised Learningcited by 25
  9. 2021A Sociotechnical View of Algorithmic Fairnesscited by 24
  10. 2022Bayes-Optimal Classifiers under Group Fairnesscited by 24
  11. 2021On Causally Disentangled Representationscited by 22
  12. 2022Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Surveycited by 22
  13. 2021Algorithm Fairness in AI for Medicine and Healthcarecited by 21
  14. 2022Transferring Fairness under Distribution Shifts via Fair Consistency Regularizationcited by 21
  15. 2022Learning fair representation with a parametric integral probability metriccited by 20
  16. 2022Fairness Amidst Non-IID Graph Data: A Literature Reviewcited by 20
  17. 2022A Survey on Fairness for Machine Learning on Graphscited by 20
  18. 2021FairMask: Better Fairness via Model-based Rebalancing of Protected Attributescited by 19
  19. 2021Latent Space Smoothing for Individually Fair Representationscited by 18
  20. 2022What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspectivecited by 18
  21. 2023FairAdaBN: Mitigating unfairness with adaptive batch normalization and its application to dermatological disease classificationcited by 18
  22. 2021Promoting Fairness through Hyperparameter Optimizationcited by 17
  23. 2021Is Disentanglement all you need? Comparing Concept-based & Disentanglement Approachescited by 17
  24. 2023On Fairness of Medical Image Classification with Multiple Sensitive Attributes via Learning Orthogonal Representationscited by 17
  25. 2023Causal Context Connects Counterfactual Fairness to Robust Prediction and Group Fairnesscited by 17
  26. 2021Fair Representation: Guaranteeing Approximate Multiple Group Fairness for Unknown Taskscited by 16
  27. 2022Fair Bayes-Optimal Classifiers Under Predictive Paritycited by 16
  28. 2021Scaling-up Disentanglement for Image Translationcited by 15
  29. 2021Disentangling Representations of Text by Masking Transformerscited by 15
  30. 2021Addressing the Topological Defects of Disentanglement via Distributed Operatorscited by 14
  31. 2022A Contrastive Objective for Learning Disentangled Representationscited by 14
  32. 2022MMD-B-Fair: Learning Fair Representations with Statistical Testingcited by 13
  33. 2023Towards a Unified Framework of Contrastive Learning for Disentangled Representationscited by 13
  34. 2024The Pursuit of Fairness in Artificial Intelligence Models: A Surveycited by 13
  35. 2021Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglementcited by 12
  36. 2021Individually Fair Gradient Boostingcited by 12
  37. 2021On Characterizing the Trade-off in Invariant Representation Learningcited by 12
  38. 2022Don't Throw it Away! The Utility of Unlabeled Data in Fair Decision Makingcited by 12

50 most cited of 196 All 196 (JSON)