mlsanityData to 7 Oct 2026

The Intersectionality Problem for Algorithmic Fairness

arXiv 2411.02569 ↗First posted 4 Nov 2024cs.LG cs.AI cs.CYcited by 5

Not on the map. Why?

Abstract (arXiv)

A yet unmet challenge in algorithmic fairness is the problem of intersectionality, that is, achieving fairness across the intersection of multiple groups -- and verifying that such fairness has been attained. Because intersectional groups tend to be small, verifying whether a model is fair raises statistical as well as moral-methodological challenges. This paper (1) elucidates the problem of intersectionality in algorithmic fairness, (2) develops desiderata to clarify the challenges underlying the problem and guide the search for potential solutions, (3) illustrates the desiderata and potential solutions by sketching a proposal using simple hypothesis testing, and (4) evaluates, partly empirically, this proposal against the proposed desiderata.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 16 of its 33 references that are in the map. First posted on arXiv 4 Nov 2024.

Builds on

16 of 33 references.

References · 16

  1. 2021Retiring Adult: New Datasets for Fair Machine Learningcited by 443
  2. 2017Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairnesscited by 381
  3. 2019Measurement and Fairnesscited by 299
  4. 2018An Intersectional Definition of Fairnesscited by 126
  5. 2018The Measure and Mismeasure of Fairnesscited by 94
  6. 2021It's COMPASlicated: The Messy Relationship between RAI Datasets and Algorithmic Fairness Benchmarkscited by 61
  7. 2022Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluationcited by 59
  8. 2019Auditing and Achieving Intersectional Fairness in Classification Problemscited by 25
  9. 2018Bayesian Modeling of Intersectional Fairness: The Variance of Biascited by 23
  10. 2022De-biasing "bias" measurementcited by 20
  11. 2023Statistical Inference for Fairness Auditingcited by 19
  12. 2022Bounding and Approximating Intersectional Fairness through Marginal Fairnesscited by 11
4 more
  1. 2020Debiasing classifiers: is reality at variance with expectation?cited by 10
  2. 2020Lale: Consistent Automated Machine Learningcited by 4
  3. 2023A Suite of Fairness Datasets for Tabular Classificationcited by 3
  4. 2023An Epistemic and Aleatoric Decomposition of Arbitrariness to Constrain the Set of Good Modelscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 2.

5 papers.

  1. 2025Size-adaptive Hypothesis Testing for Fairnesscited by 1
  2. 2025Toward Substantive Intersectional Algorithmic Fairness: Desiderata for a Feminist Approachcited by 0
  3. 2025Auditability and the Landscape of Distance to Multicalibrationcited by 0
  4. 2026MESD: A Risk-Sensitive Metric for Explanation Fairness Across Intersectional Subgroupscited by 0
  5. 2026Position: Fairness Failure in Generative Models is an Evaluation Problemcited by 0