mlsanityData to 7 Oct 2026

Equality of Opportunity in Supervised Learning

arXiv 1610.02413 ↗First posted 7 Oct 2016cs.LGcited by 2,000

Not on the map. Why?

Cited by 22 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose a criterion for discrimination against a specified sensitive attribute in supervised learning, where the goal is to predict some target based on available features. Assuming data about the predictor, target, and membership in the protected group are available, we show how to optimally adjust any learned predictor so as to remove discrimination according to our definition. Our framework also improves incentives by shifting the cost of poor classification from disadvantaged groups to the decision maker, who can respond by improving the classification accuracy. In line with other studies, our notion is oblivious: it depends only on the joint statistics of the predictor, the target and the protected attribute, but not on interpretation of individualfeatures. We study the inherent limits of defining and identifying biases based on such oblivious measures, outlining what can and cannot be inferred from different oblivious tests. We illustrate our notion using a case study of FICO credit scores.

Key facts. Cited by 2,000 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Oct 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 1; 2021: 325; 2022: 387; 2023: 385; 2024: 352; 2025: 336; 2026: 213.

2,000 papers.

Sort:

By area:

  1. 2023A Survey on Evaluation of Large Language Modelscited by 1,227
  2. 2020Aligning AI With Shared Human Valuescited by 706
  3. 2023Bias and Fairness in Large Language Models: A Surveycited by 626
  4. 2021Just Train Twice: Improving Group Robustness without Training Group Informationcited by 522
  5. 2021Retiring Adult: New Datasets for Fair Machine Learningcited by 443
  6. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  7. 2022Last Layer Re-Training is Sufficient for Robustness to Spurious Correlationscited by 379
  8. 2021A Field Guide to Federated Optimizationcited by 312
  9. 2021Unsolved Problems in ML Safetycited by 291
  10. 2023From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Modelscited by 257
  11. 2024Self-Preference Bias in LLM-as-a-Judgecited by 248
  12. 2021Trustworthy AI: From Principles to Practicescited by 206
38 more
  1. 2021Societal Biases in Language Generation: Progress and Challengescited by 201
  2. 2021Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyondcited by 177
  3. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 160
  4. 2021A survey on datasets for fairness-aware machine learningcited by 157
  5. 2022On Feature Learning in the Presence of Spurious Correlationscited by 145
  6. 2024Benchmark Data Contamination of Large Language Models: A Surveycited by 138
  7. 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
  8. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  9. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  10. 2021Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspectivecited by 116
  11. 2022Jury Learning: Integrating Dissenting Voices into Machine Learning Modelscited by 115
  12. 2021FairFed: Enabling Group Fairness in Federated Learningcited by 114
  13. 2021Fair Mixup: Fairness via Interpolationcited by 109
  14. 2021DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networkscited by 109
  15. 2021A Clarification of the Nuances in the Fairness Metrics Landscapecited by 98
  16. 2022Linear Adversarial Concept Erasurecited by 98
  17. 2021Challenges in Automated Debiasing for Toxic Language Detectioncited by 95
  18. 2021Trustworthy AI: A Computational Perspectivecited by 93
  19. 2021Bias in Machine Learning Software: Why? How? What to do?cited by 92
  20. 2021EDITS: Modeling and Mitigating Data Bias for Graph Neural Networkscited by 92
  21. 2024Large Language Models are Geographically Biasedcited by 91
  22. 2021Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Searchcited by 90
  23. 2022Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?cited by 89
  24. 2023Verbosity Bias in Preference Labeling by Large Language Modelscited by 89
  25. 2021Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metricscited by 83
  26. 2022Towards Adversarial Evaluations for Inexact Machine Unlearningcited by 82
  27. 2022Distilling Model Failures as Directions in Latent Spacecited by 82
  28. 2022Fairness in Graph Mining: A Surveycited by 76
  29. 2021User-oriented Fairness in Recommendationcited by 75
  30. 2021Label-Imbalanced and Group-Sensitive Classification under Overparameterizationcited by 74
  31. 2023Fairlearn: Assessing and Improving Fairness of AI Systemscited by 74
  32. 2021Towards Unbiased and Accurate Deferral to Multiple Expertscited by 71
  33. 2022Fair Contrastive Learning for Facial Attribute Classificationcited by 71
  34. 2023DeAR: Debiasing Vision-Language Models with Additive Residualscited by 70
  35. 2023Fast Model Debias with Machine Unlearningcited by 70
  36. 2024Preserving Fairness Generalization in Deepfake Detectioncited by 70
  37. 2021FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learningcited by 68
  38. 2022Synthetic Data -- what, why and how?cited by 66

50 most cited of 2,000 All 2,000 (JSON)