mlsanityData to 14 Oct 2026

Characterizing Fairness Over the Set of Good Models Under Selective Labels

arXiv 2101.00352 ↗First posted 2 Jan 2021cs.LG stat.MLcited by 65

Not on the map. Why?

Abstract (arXiv)

Algorithmic risk assessments are used to inform decisions in a wide variety of high-stakes settings. Often multiple predictive models deliver similar overall performance but differ markedly in their predictions for individual cases, an empirical phenomenon known as the "Rashomon Effect." These models may have different properties over various groups, and therefore have different predictive fairness properties. We develop a framework for characterizing predictive fairness properties over the set of models that deliver similar overall performance, or "the set of good models." Our framework addresses the empirically relevant challenge of selectively labelled data in the setting where the selection decision and outcome are unconfounded given the observed data features. Our framework can be used to 1) replace an existing model with one that has better fairness properties; or 2) audit for predictive bias. We illustrate these uses cases on a real-world credit-scoring task and a recidivism prediction task.

Key facts. Cited by 65 papers in the map (data through 14 Oct 2026). Builds on 21 of its 63 references that are in the map. First posted on arXiv 2 Jan 2021.

Builds on

21 of 63 references.

References · 21

  1. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  2. 2014Certifying and removing disparate impactcited by 715
  3. 2018A Reductions Approach to Fair Classificationcited by 587
  4. 2017On Fairness and Calibrationcited by 406
  5. 2017Algorithmic decision making and the cost of fairnesscited by 403
  6. 2018All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneouslycited by 373
  7. 2018Improving fairness in machine learning systems: What do industry practitioners need?cited by 262
  8. 2018Empirical Risk Minimization under Fairness Constraintscited by 226
  9. 2018Multiaccuracy: Black-Box Post-Processing for Fairness in Classificationcited by 222
  10. 2015Doctor AI: Predicting Clinical Events via Recurrent Neural Networkscited by 208
  11. 2019Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practicescited by 174
  12. 2019Fair Regression: Quantitative Definitions and Reduction-based Algorithmscited by 168
9 more
  1. 2019Predictive Multiplicity in Classificationcited by 166
  2. 2019Counterfactual Risk Assessments, Evaluation, and Fairnesscited by 59
  3. 2018Two-Player Games for Efficient Non-Convex Constrained Optimizationcited by 55
  4. 2018The age of secrecy and unfairness in recidivism predictioncited by 53
  5. 2018Residual Unfairness in Fair Machine Learning from Prejudiced Datacited by 49
  6. 2019Equal Opportunity in Online Classification with Partial Feedbackcited by 35
  7. 2019Variable Importance Clouds: A Way to Explore Variable Importance for the Set of Good Modelscited by 19
  8. 2017Fairer and more accurate, but for whom?cited by 13
  9. 2019Deep Generative Models for Reject Inference in Credit Scoringcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 5; 2022: 12; 2023: 12; 2024: 16; 2025: 13; 2026: 7.

65 papers.

Sort:

  1. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 367
  2. 2024Amazing Things Come From Having Many Good Modelscited by 55
  3. 2022Rashomon Capacity: A Metric for Predictive Multiplicity in Classificationcited by 47
  4. 2022Predictive Multiplicity in Probabilistic Classificationcited by 44
  5. 2023A Path to Simpler Models Starts With Noisecited by 33
  6. 2022A Validity Perspective on Evaluating the Justified Use of Data-driven Decision-making Algorithmscited by 30
  7. 2024Robust Counterfactual Explanations in Machine Learning: A Surveycited by 29
  8. 2021Characterizing the risk of fairwashingcited by 21
  9. 2022Rank List Sensitivity of Recommender Systems to Interaction Perturbationscited by 20
  10. 2023Arbitrary Decisions are a Hidden Cost of Differentially Private Trainingcited by 19
  11. 2024Dropout-Based Rashomon Set Exploration for Efficient Predictive Multiplicity Estimationcited by 18
  12. 2023The Dataset Multiplicity Problem: How Unreliable Data Impacts Predictionscited by 17
38 more
  1. 2025Systemizing Multiplicity: The Curious Case of Arbitrariness in Machine Learningcited by 17
  2. 2022What's the Harm? Sharp Bounds on the Fraction Negatively Affected by Treatmentcited by 15
  3. 2023Recourse under Model Multiplicity via Argumentative Ensembling (Technical Report)cited by 15
  4. 2024Predictive Churn with the Set of Good Modelscited by 15
  5. 2021FADE: FAir Double Ensemble Learning for Observable and Counterfactual Outcomescited by 13
  6. 2021The Impact of Algorithmic Risk Assessments on Human Predictions and its Analysis via Crowdsourcing Studiescited by 13
  7. 2022TimberTrek: Exploring and Curating Sparse Decision Trees with Interactive Visualizationcited by 13
  8. 2024Algorithmic Arbitrariness in Content Moderationcited by 13
  9. 2022Computing the Collection of Good Models for Rule Listscited by 12
  10. 2023Multi-Target Multiplicity: Flexibility and Fairness in Target Specification under Resource Constraintscited by 11
  11. 2024Efficient Exploration of the Rashomon Set of Rule Set Modelscited by 10
  12. 2025Be Intentional About Fairness!: Fairness, Size, and Multiplicity in the Rashomon Setcited by 10
  13. 2022Equalizing Credit Opportunity in Algorithms: Aligning Algorithmic Fairness Research with U.S. Fair Lending Regulationcited by 9
  14. 2022Robust Design and Evaluation of Predictive Algorithms under Unobserved Confoundingcited by 8
  15. 2024The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learningcited by 8
  16. 2024What Constitutes a Less Discriminatory Algorithm?cited by 8
  17. 2022Perspectives on Incorporating Expert Feedback into Model Updatescited by 7
  18. 2023Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Toolscited by 7
  19. 2023A Bayesian Spatial Model to Correct Under-Reporting in Urban Crowdsourcingcited by 6
  20. 2024Quantifying Prediction Consistency Under Fine-Tuning Multiplicity in Tabular LLMscited by 6
  21. 2022Individually Fair Learning with One-Sided Feedbackcited by 5
  22. 2023Algorithmic Censoring in Dynamic Learning Systemscited by 5
  23. 2023Arbitrariness Lies Beyond the Fairness-Accuracy Frontiercited by 5
  24. 2023Minimum Levels of Interpretability for Artificial Moral Agentscited by 5
  25. 2025Fairness and Sparsity within Rashomon sets: Enumeration-Free Exploration and Characterizationcited by 4
  26. 2021Unpacking the Black Box: Regulating Algorithmic Decisionscited by 3
  27. 2022Differentially Private Sampling from Rashomon Sets, and the Universality of Langevin Diffusion for Convex Optimizationcited by 3
  28. 2024Monotone Individual Fairnesscited by 3
  29. 2025Perils of Label Indeterminacy: A Case Study on Prediction of Neurological Recovery After Cardiac Arrestcited by 3
  30. 2024Fair Classification with Partial Feedback: An Exploration-Based Data Collection Approachcited by 2
  31. 2024Predictive Performance Comparison of Decision Policies Under Confoundingcited by 2
  32. 2024A Conceptual Framework for Ethical Evaluation of Machine Learning Systemscited by 2
  33. 2024The Disparate Benefits of Deep Ensemblescited by 2
  34. 2025Welfare as a Guiding Principle for Machine Learning -- From Compass, to Lens, to Roadmapcited by 2
  35. 2026The Subjectivity of Monoculturecited by 2
  36. 2026Fairness under uncertainty in sequential decisionscited by 2
  37. 2023Rethinking Algorithmic Fairness for Human-AI Collaborationcited by 1
  38. 2024Auditing and Enforcing Conditional Fairness via Optimal Transportcited by 1

50 most cited of 65 All 65 (JSON)