mlsanityData to 7 Oct 2026

Technical Challenges for Training Fair Neural Networks

arXiv 2102.06764 ↗First posted 12 Feb 2021cs.LG cs.AI cs.CYcited by 20

Not on the map. Why?

Abstract (arXiv)

As machine learning algorithms have been widely deployed across applications, many concerns have been raised over the fairness of their predictions, especially in high stakes settings (such as facial recognition and medical imaging). To respond to these concerns, the community has proposed and formalized various notions of fairness as well as methods for rectifying unfair behavior. While fairness constraints have been studied extensively for classical models, the effectiveness of methods for imposing fairness on deep neural networks is unclear. In this paper, we observe that these large models overfit to fairness objectives, and produce a range of unintended and undesirable consequences. We conduct our experiments on both facial recognition and automated medical diagnosis datasets using state-of-the-art architectures.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 36 of its 69 references that are in the map. First posted on arXiv 12 Feb 2021.

Builds on

36 of 69 references.

References · 36

  1. 2016Densely Connected Convolutional Networkscited by 6,691
  2. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  3. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  4. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
  5. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
  6. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 733
  7. 2014Certifying and removing disparate impactcited by 715
  8. 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 671
  9. 2018A Reductions Approach to Fair Classificationcited by 585
  10. 2019Agnostic Federated Learningcited by 451
  11. 2017Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairnesscited by 381
  12. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 368
24 more
  1. 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 363
  2. 2018Learning Adversarially Fair and Transferable Representationscited by 353
  3. 2018Improving fairness in machine learning systems: What do industry practitioners need?cited by 262
  4. 2019Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigationcited by 252
  5. 2020Fairness without Demographics through Adversarially Reweighted Learningcited by 251
  6. 2018Empirical Risk Minimization under Fairness Constraintscited by 226
  7. 2015Censoring Representations with an Adversarycited by 191
  8. 2018Fairness of Exposure in Rankingscited by 189
  9. 2017Data Decisions and Theoretical Implications when Adversarially Learning Fair Representationscited by 165
  10. 2020CheXclusion: Fairness gaps in deep chest X-ray classifierscited by 153
  11. 2020Minimax Pareto Fairness: A Multi Objective Perspectivecited by 152
  12. 2017Fairness in Machine Learning: Lessons from Political Philosophycited by 148
  13. 2019Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learningcited by 145
  14. 2018Equity of Attention: Amortizing Individual Fairness in Rankingscited by 124
  15. 2017Fairness Testing: Testing Software for Discriminationcited by 123
  16. 2021LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognitioncited by 92
  17. 2020Saving Face: Investigating the Ethical Concerns of Facial Recognition Auditingcited by 89
  18. 2019Putting Fairness Principles into Practice: Challenges, Metrics, and Improvementscited by 70
  19. 2020Fairness Through Robustness: Investigating Robustness Disparity in Deep Learningcited by 55
  20. 2019On the Long-term Impact of Algorithmic Decision Policies: Effort Unfairness and Feature Segregation through Social Learningcited by 48
  21. 2018FNNC: Achieving Fairness through Neural Networkscited by 43
  22. 2020On Adversarial Bias and the Robustness of Fair Machine Learningcited by 36
  23. 2020Minimax Group Fairness: Algorithms and Experimentscited by 17
  24. 2018On Microtargeting Socially Divisive Ads: A Case Study of Russia-Linked Ad Campaigns on Facebookcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 8; 2023: 4; 2024: 4; 2025: 2; 2026: 1.

20 papers.

Sort:

By area:

  1. 2022AUC Maximization in the Era of Big Data and AI: A Surveycited by 100
  2. 2022Diagnosing failures of fairness transfer across distribution shift in real-world medical settingscited by 45
  3. 2023Model Agnostic Sample Reweighting for Out-of-Distribution Learningcited by 43
  4. 2024Multilinear Mixture of Experts: Scalable Expert Specialization through Factorizationcited by 28
  5. 2022Addressing Fairness Issues in Deep Learning-Based Medical Image Analysis: A Systematic Reviewcited by 27
  6. 2022Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognitioncited by 26
  7. 2023Last-Layer Fairness Fine-tuning is Simple and Effective for Neural Networkscited by 17
  8. 2022FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Datacited by 13
  9. 2022Equal Improvability: A New Fairness Notion Considering the Long-term Impactcited by 13
  10. 2021Deep AUC Maximization for Medical Image Classification: Challenges and Opportunitiescited by 6
  11. 2022Malign Overfitting: Interpolation Can Provably Preclude Invariancecited by 6
  12. 2022Fairness via In-Processing in the Over-parameterized Regime: A Cautionary Talecited by 4
8 more
  1. 2024Looking Beyond What You See: An Empirical Analysis on Subgroup Intersectional Fairness for Multi-label Chest X-ray Classification Using Social Determinants of Racial Health Inequitiescited by 3
  2. 2023Pushing the Accuracy-Group Robustness Frontier with Introspective Self-playcited by 2
  3. 2024Provable Optimization for Adversarial Fair Self-supervised Contrastive Learningcited by 2
  4. 2024Enhancing Fairness through Reweighting: A Path to Attain the Sufficiency Rulecited by 1
  5. 2023The Fairness Stitch: Unveiling the Potential of Model Stitching in Neural Network De-Biasingcited by 0
  6. 2025Disentanglement and Assessment of Shortcuts in Ophthalmological Retinal Imaging Examscited by 0
  7. 2025SWiFT: Soft-Mask Weight Fine-tuning for Bias Mitigationcited by 0
  8. 2026Intra-Fairness Dynamics: The Bias Spillover Effect in Targeted LLM Alignmentcited by 0