mlsanityData to 7 Oct 2026

Learning Adversarially Fair and Transferable Representations

arXiv 1802.06309 ↗First posted 17 Feb 2018cs.LG stat.MLcited by 353

Not on the map. Why?

Abstract (arXiv)

In this paper, we advocate for representation learning as the key to mitigating unfair prediction outcomes downstream. Motivated by a scenario where learned representations are used by third parties with unknown objectives, we propose and explore adversarial representation learning as a natural method of ensuring those parties act fairly. We connect group fairness (demographic parity, equalized odds, and equal opportunity) to different adversarial objectives. Through worst-case theoretical guarantees and experimental validation, we show that the choice of this objective is crucial to fair prediction. Furthermore, we present the first in-depth experimental demonstration of fair transfer learning and demonstrate empirically that our learned representations admit fair predictions on new tasks while maintaining utility, an essential goal of fair representation learning.

Key facts. Cited by 353 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 65; 2022: 87; 2023: 68; 2024: 44; 2025: 61; 2026: 28.

353 papers.

Sort:

By area:

  1. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  2. 2023Debiasing Vision-Language Models via Biased Promptscited by 147
  3. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  4. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  5. 2021Fair Mixup: Fairness via Interpolationcited by 109
  6. 2021Towards Principled Disentanglement for Domain Generalizationcited by 91
  7. 2022Fair Contrastive Learning for Facial Attribute Classificationcited by 71
  8. 2022MEDFAIR: Benchmarking Fairness for Medical Imagingcited by 66
  9. 2021Causally motivated Shortcut Removal Using Auxiliary Labelscited by 55
  10. 2022Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifierscited by 53
  11. 2022Improving the Fairness of Chest X-ray Classifierscited by 52
  12. 2021Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learningcited by 50
38 more
  1. 2022Fair and Optimal Classification via Post-Processingcited by 50
  2. 2024FairMedFM: Fairness Benchmarking for Medical Imaging Foundation Modelscited by 47
  3. 2021A Step Toward More Inclusive People Annotations for Fairnesscited by 46
  4. 2021Controllable Guarantees for Fair Outcomes via Contrastive Information Estimationcited by 45
  5. 2022The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanationscited by 41
  6. 2023Improving Fairness in Deepfake Detectioncited by 40
  7. 2021Fair Normalizing Flowscited by 38
  8. 2021PASS: Protected Attribute Suppression System for Mitigating Bias in Face Recognitioncited by 38
  9. 2023Principled Approaches for Learning to Defer with Multiple Expertscited by 38
  10. 2024CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?cited by 35
  11. 2021Societal Biases in Retrieved Contents: Measurement Framework and Adversarial Mitigation for BERT Rankerscited by 34
  12. 2021Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task Learningcited by 34
  13. 2021TabFairGAN: Fair Tabular Data Generation with Generative Adversarial Networkscited by 34
  14. 2023FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methodscited by 33
  15. 2021Fairness for Image Generation with Uncertain Sensitive Attributescited by 31
  16. 2022Learning Fair Representation via Distributional Contrastive Disentanglementcited by 31
  17. 2022On Learning Fairness and Accuracy on Multiple Subgroupscited by 31
  18. 2021Towards Robust Classification Model by Counterfactual and Invariant Data Generationcited by 30
  19. 2023Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectivescited by 30
  20. 2021Unbiased Graph Embedding with Biased Graph Observationscited by 28
  21. 2022Understanding Instance-Level Impact of Fairness Constraintscited by 27
  22. 2023Survey of Social Bias in Vision-Language Modelscited by 26
  23. 2024Realizable H-Consistent and Bayes-Consistent Loss Functions for Learning to Defercited by 26
  24. 2021Conditional Contrastive Learning for Improving Fairness in Self-Supervised Learningcited by 25
  25. 2023Parameter-efficient Modularised Bias Mitigation via AdapterFusioncited by 25
  26. 2021A Sociotechnical View of Algorithmic Fairnesscited by 24
  27. 2023Fairness and Accuracy under Domain Generalizationcited by 24
  28. 2022FairVFL: A Fair Vertical Federated Learning Framework with Contrastive Adversarial Learningcited by 23
  29. 2023Efficient fair PCA for fair representation learningcited by 23
  30. 2023Towards Fair Graph Neural Networks via Graph Counterfactualcited by 23
  31. 2023FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysiscited by 23
  32. 2022Optimising Equal Opportunity Fairness in Model Trainingcited by 22
  33. 2022Fair Representation Learning through Implicit Path Alignmentcited by 22
  34. 2022Freeze then Train: Towards Provable Representation Learning under Spurious Correlations and Feature Noisecited by 22
  35. 2021Fairness without the sensitive attribute via Causal Variational Autoencodercited by 21
  36. 2021Algorithm Fairness in AI for Medicine and Healthcarecited by 21
  37. 2021Group-Aware Threshold Adaptation for Fair Classificationcited by 21
  38. 2022Transferring Fairness under Distribution Shifts via Fair Consistency Regularizationcited by 21

50 most cited of 353 All 353 (JSON)