mlsanityData to 7 Oct 2026

A Reduction to Binary Approach for Debiasing Multiclass Datasets

arXiv 2205.15860 ↗First posted 31 May 2022cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

We propose a novel reduction-to-binary (R2B) approach that enforces demographic parity for multiclass classification with non-binary sensitive attributes via a reduction to a sequence of binary debiasing tasks. We prove that R2B satisfies optimality and bias guarantees and demonstrate empirically that it can lead to an improvement over two baselines: (1) treating multiclass problems as multi-label by debiasing labels independently and (2) transforming the features instead of the labels. Surprisingly, we also demonstrate that independent label debiasing yields competitive results in most (but not all) settings. We validate these conclusions on synthetic and real-world datasets from social science, computer vision, and healthcare.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 34 of its 73 references that are in the map. First posted on arXiv 31 May 2022.

Builds on

34 of 73 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2021Convex optimizationcited by 2,479
  4. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  5. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  6. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  7. 2016Semantics derived automatically from language corpora contain human-like biasescited by 894
  8. 2014Certifying and removing disparate impactcited by 715
  9. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  10. 2018A Reductions Approach to Fair Classificationcited by 585
  11. 2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraintscited by 420
  12. 2017Algorithmic decision making and the cost of fairnesscited by 402
22 more
  1. 2017Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairnesscited by 381
  2. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 368
  3. 2018Learning Adversarially Fair and Transferable Representationscited by 353
  4. 2019Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigationcited by 252
  5. 2018Women also Snowboard: Overcoming Bias in Captioning Modelscited by 236
  6. 2019Causality matters in medical imagingcited by 193
  7. 2019Towards Fairer Datasets: Filtering and Balancing the Distribution of the People Subtree in the ImageNet Hierarchycited by 156
  8. 2018Classification with Fairness Constraints: A Meta-Algorithm with Provable Guaranteescited by 146
  9. 2019Inherent Tradeoffs in Learning Fair Representationscited by 144
  10. 2020REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasetscited by 136
  11. 2019A deep learning system for differential diagnosis of skin diseasescited by 118
  12. 2020Mitigating Bias in Calibration Error Estimationcited by 100
  13. 2021Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Testscited by 77
  14. 2021Does Your Dermatology Classifier Know What It Doesn't Know? Detecting the Long-Tail of Unseen Conditionscited by 68
  15. 2019Mathematical Notions vs. Human Perception of Fairness: A Descriptive Approach to Fairness for Machine Learningcited by 57
  16. 2016A statistical framework for fair predictive algorithmscited by 37
  17. 2019On the Consistency of Top-k Surrogate Lossescited by 35
  18. 2015A General Analysis of the Convergence of ADMMcited by 22
  19. 2021A Near-Optimal Algorithm for Debiasing Trained Machine Learning Modelscited by 19
  20. 2020Fairness with Overlapping Groupscited by 12
  21. 2020Uncovering the Bias in Facial Expressionscited by 12
  22. 2014Conditional Probability Tree Estimation Analysis and Algorithmscited by 10

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 6; 2025: 1.

9 papers.

  1. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  2. 2024CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?cited by 35
  3. 2023Learning Optimal Fair Scoring Systems for Multi-Class Classificationcited by 8
  4. 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
  5. 2024Evaluating Model Bias Requires Characterizing its Mistakescited by 3
  6. 2024Studying and Mitigating Biases in Sign Language Understanding Modelscited by 1
  7. 2024SimClone: Detecting Tabular Data Clones using Value Similaritycited by 0
  8. 2024Fair Class-Incremental Learning using Sample Weightingcited by 0
  9. 2025A Critical Review of Predominant Bias in Neural Networkscited by 0