mlsanityData to 7 Oct 2026

On Fairness and Calibration

arXiv 1709.02012 ↗First posted 6 Sep 2017cs.LG cs.CY stat.MLcited by 406

Not on the map. Why?

Abstract (arXiv)

The machine learning community has become increasingly concerned with the potential for bias and discrimination in predictive models. This has motivated a growing line of work on what it means for a classification procedure to be "fair." In this paper, we investigate the tension between minimizing error disparity across different population groups while maintaining calibrated probability estimates. We show that calibration is compatible only with a single error constraint (i.e. equal false-negatives rates across groups), and show that any algorithm that satisfies this relaxation is no better than randomizing a percentage of predictions for an existing classifier. These unsettling findings, which extend and generalize existing results, are empirically confirmed on several datasets.

Key facts. Cited by 406 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Sep 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 83; 2022: 89; 2023: 93; 2024: 62; 2025: 41; 2026: 38.

406 papers.

Sort:

By area:

  1. 2021Just Train Twice: Improving Group Robustness without Training Group Informationcited by 522
  2. 2022Last Layer Re-Training is Sufficient for Robustness to Spurious Correlationscited by 379
  3. 2021Trustworthy AI: From Principles to Practicescited by 206
  4. 2022On Feature Learning in the Presence of Spurious Correlationscited by 145
  5. 2021On Calibration and Out-of-domain Generalizationcited by 134
  6. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  7. 2021Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspectivecited by 116
  8. 2023HRS-Bench: Holistic, Reliable and Scalable Benchmark for Text-to-Image Modelscited by 94
  9. 2021Trustworthy AI: A Computational Perspectivecited by 93
  10. 2021EDITS: Modeling and Mitigating Data Bias for Graph Neural Networkscited by 92
  11. 2021Soft Calibration Objectives for Neural Networkscited by 89
  12. 2021Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibrationcited by 79
38 more
  1. 2023Calibration in Deep Learning: A Survey of the State-of-the-Artcited by 72
  2. 2021Towards Unbiased and Accurate Deferral to Multiple Expertscited by 71
  3. 2021Classifier Calibration: A survey on how to assess and improve predicted class probabilitiescited by 71
  4. 2023DeAR: Debiasing Vision-Language Models with Additive Residualscited by 70
  5. 2024FairCLIP: Harnessing Fairness in Vision-Language Learningcited by 69
  6. 2022MEDFAIR: Benchmarking Fairness for Medical Imagingcited by 66
  7. 2021Characterizing Fairness Over the Set of Good Models Under Selective Labelscited by 65
  8. 2021Fairness in Credit Scoring: Assessment, Implementation and Profit Implicationscited by 65
  9. 2022Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluationcited by 59
  10. 2023FUTURE-AI: International consensus guideline for trustworthy and deployable artificial intelligence in healthcarecited by 59
  11. 2021Fairness in Cardiac MR Image Analysis: An Investigation of Bias Due to Data Imbalance in Deep Learning Based Segmentationcited by 57
  12. 2022Improving the Fairness of Chest X-ray Classifierscited by 52
  13. 2022Fair and Optimal Classification via Post-Processingcited by 50
  14. 2021Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipelinecited by 49
  15. 2022How Different Groups Prioritize Ethical Values for Responsible AIcited by 49
  16. 2021Online Multivalid Learning: Means, Moments, and Prediction Intervalscited by 48
  17. 2021Sample Selection for Fair and Robust Trainingcited by 48
  18. 2021Knowing More About Questions Can Help: Improving Calibration in Question Answeringcited by 47
  19. 2022Discover and Mitigate Unknown Biases with Debiasing Alternate Networkscited by 47
  20. 2021Towards Fair Classifiers Without Sensitive Attributes: Exploring Biases in Related Featurescited by 45
  21. 2022Low-Degree Multicalibrationcited by 44
  22. 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomycited by 44
  23. 2021Deep Cox Mixtures for Survival Regressioncited by 43
  24. 2022Causal Fairness Analysiscited by 42
  25. 2022The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanationscited by 41
  26. 2021Your fairness may vary: Pretrained language model fairness in toxic text classificationcited by 38
  27. 2022Achieving Fairness at No Utility Cost via Data Reweighing with Influencecited by 38
  28. 2022Representation Bias in Data: A Survey on Identification and Resolution Techniquescited by 37
  29. 2024Assessment of Multimodal Large Language Models in Alignment with Human Valuescited by 36
  30. 2021Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task Learningcited by 34
  31. 2021Selective Regression Under Fairness Criteriacited by 34
  32. 2021Evaluating Fairness of Machine Learning Models Under Uncertain and Incomplete Informationcited by 33
  33. 2022Fairness Reprogrammingcited by 33
  34. 2022On Learning Fairness and Accuracy on Multiple Subgroupscited by 31
  35. 2023Arbitrariness and Social Prediction: The Confounding Role of Variance in Fair Classificationcited by 31
  36. 2022A Comprehensive Empirical Study of Bias Mitigation Methods for Machine Learning Classifierscited by 30
  37. 2023On Generalized Degree Fairness in Graph Neural Networkscited by 28
  38. 2021Fairness in Ranking under Uncertaintycited by 27

50 most cited of 406 All 406 (JSON)