mlsanityData to 7 Oct 2026

An Algorithmic Framework for Bias Bounties

arXiv 2201.10408 ↗First posted 25 Jan 2022cs.LG cs.CY cs.DScited by 19

Not on the map. Why?

Abstract (arXiv)

We propose and analyze an algorithmic framework for "bias bounties": events in which external participants are invited to propose improvements to a trained model, akin to bug bounty events in software and security. Our framework allows participants to submit arbitrary subgroup improvements, which are then algorithmically incorporated into an updated model. Our algorithm has the property that there is no tension between overall and subgroup accuracies, nor between different subgroup accuracies, and it enjoys provable convergence to either the Bayes optimal model or a state in which no further improvements can be found by the participants. We provide formal analyses of our framework, experimental evaluation, and findings from a preliminary bias bounty event.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 25 of its 44 references that are in the map. First posted on arXiv 25 Jan 2022.

Builds on

25 of 44 references.

References · 25

  1. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  2. 2018Datasheets for Datasetscited by 1,371
  3. 2018Model Cards for Model Reportingcited by 1,068
  4. 2018A Reductions Approach to Fair Classificationcited by 585
  5. 2021Retiring Adult: New Datasets for Fair Machine Learningcited by 443
  6. 2017Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairnesscited by 381
  7. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 368
  8. 2018Multiaccuracy: Black-Box Post-Processing for Fairness in Classificationcited by 221
  9. 2020Minimax Pareto Fairness: A Multi Objective Perspectivecited by 152
  10. 2014Preserving Statistical Validity in Adaptive Data Analysiscited by 102
  11. 2015Algorithmic Stability for Adaptive Data Analysiscited by 88
  12. 2018An Empirical Study of Rich Subgroup Fairness for Machine Learningcited by 81
13 more
  1. 2015Generalization in Adaptive Data Analysis and Holdout Reusecited by 76
  2. 2020Outcome Indistinguishabilitycited by 74
  3. 2015The Ladder: A Reliable Leaderboard for Machine Learning Competitionscited by 67
  4. 2020Moment Multicalibration for Uncertainty Estimationcited by 63
  5. 2019Metric Learning for Individual Fairnesscited by 51
  6. 2019Recovering from Biased Data: Can Fairness Constraints Improve Accuracy?cited by 50
  7. 2021Online Multivalid Learning: Means, Moments, and Prediction Intervalscited by 48
  8. 2021Multi-group Agnostic PAC Learnabilitycited by 42
  9. 2019A New Analysis of Differential Privacy's Generalization Guaranteescited by 36
  10. 2018Probably Approximately Metric-Fair Learningcited by 29
  11. 2019Advancing subgroup fairness via sleeping expertscited by 28
  12. 2021Simple and near-optimal algorithms for hidden stratification and multi-group learningcited by 26
  13. 2021Lexicographically Fair Learning: Algorithms and Generalizationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 4; 2024: 7; 2025: 3; 2026: 1.

19 papers.

Sort:

  1. 2022Minimax AUC Fairness: Efficient Algorithm with Provable Convergencecited by 16
  2. 2022Reconciling Individual Probability Forecastscited by 14
  3. 2024Fair Risk Control: A Generalized Framework for Calibrating Multi-group Fairness Riskscited by 13
  4. 2023Bound by the Bounty: Collaboratively Shaping Evaluation Processes for Queer AI Harmscited by 10
  5. 2022Comparative Learning: A Sample Complexity Theory for Two Hypothesis Classescited by 8
  6. 2023The AI Incident Database as an Educational Tool to Raise Awareness of AI Harms: A Classroom Exploration of Efficacy, Limitations, & Future Improvementscited by 8
  7. 2024Group-wise oracle-efficient algorithms for online multi-group learningcited by 8
  8. 2024Multi-group Learning for Hierarchical Groupscited by 7
  9. 2024Addressing the regulatory gap: moving towards an EU AI audit ecosystem beyond the AI Act by including civil societycited by 7
  10. 2022When Personalization Harms: Reconsidering the Use of Group Attributes in Predictioncited by 6
  11. 2023Oracle Efficient Algorithms for Groupwise Regretcited by 6
  12. 2023Participatory Personalization in Classificationcited by 5
7 more
  1. 2024Reconciling Model Multiplicity for Downstream Decision Makingcited by 5
  2. 2025From Individual Experience to Collective Evidence: A Reporting-Based Framework for Identifying Systemic Harmscited by 3
  3. 2026Group-realizable multi-group learning by minimizing empirical riskcited by 2
  4. 2024Diversified Ensembling: An Experiment in Crowdsourced Machine Learningcited by 1
  5. 2024Adjusting Pretrained Backbones for Performativitycited by 0
  6. 2025"Who experiences large model decay and why?" A Hierarchical Framework for Diagnosing Heterogeneous Performance Driftcited by 0
  7. 2025The Current State of AI Bias Bounties: An Overview of Existing Programmes and Researchcited by 0