The Intersectionality Problem for Algorithmic Fairness

Johannes Himmelreich, Arbie Hsu, Ellen Veomett, Kristian Lum
Proceedings of the Algorithmic Fairness Through the Lens of Metrics and Evaluation, PMLR 279:68-95, 2025.

Abstract

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 fairnesshas been attained. Because intersectional groups tend to be small, verifying whether amodel is fair raises statistical as well as moral-methodological challenges. This paper (1)elucidates the problem of intersectionality in algorithmic fairness, (2) develops desiderata toclarify the challenges underlying the problem and guide the search for potential solutions,(3) illustrates the desiderata and potential solutions by sketching a proposal using simplehypothesis testing, and (4) evaluates, partly empirically, this proposal against the proposeddesiderata.

Cite this Paper

BibTeX
@InProceedings{pmlr-v279-himmelreich25a, title = {The Intersectionality Problem for Algorithmic Fairness}, author = {Himmelreich, Johannes and Hsu, Arbie and Veomett, Ellen and Lum, Kristian}, booktitle = {Proceedings of the Algorithmic Fairness Through the Lens of Metrics and Evaluation}, pages = {68--95}, year = {2025}, editor = {Rateike, Miriam and Dieng, Awa and Watson-Daniels, Jamelle and Fioretto, Ferdinando and Farnadi, Golnoosh}, volume = {279}, series = {Proceedings of Machine Learning Research}, month = {14 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v279/main/assets/himmelreich25a/himmelreich25a.pdf}, url = {https://proceedings.mlr.press/v279/himmelreich25a.html}, abstract = {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 fairnesshas been attained. Because intersectional groups tend to be small, verifying whether amodel is fair raises statistical as well as moral-methodological challenges. This paper (1)elucidates the problem of intersectionality in algorithmic fairness, (2) develops desiderata toclarify the challenges underlying the problem and guide the search for potential solutions,(3) illustrates the desiderata and potential solutions by sketching a proposal using simplehypothesis testing, and (4) evaluates, partly empirically, this proposal against the proposeddesiderata.} }
Endnote
%0 Conference Paper %T The Intersectionality Problem for Algorithmic Fairness %A Johannes Himmelreich %A Arbie Hsu %A Ellen Veomett %A Kristian Lum %B Proceedings of the Algorithmic Fairness Through the Lens of Metrics and Evaluation %C Proceedings of Machine Learning Research %D 2025 %E Miriam Rateike %E Awa Dieng %E Jamelle Watson-Daniels %E Ferdinando Fioretto %E Golnoosh Farnadi %F pmlr-v279-himmelreich25a %I PMLR %P 68--95 %U https://proceedings.mlr.press/v279/himmelreich25a.html %V 279 %X 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 fairnesshas been attained. Because intersectional groups tend to be small, verifying whether amodel is fair raises statistical as well as moral-methodological challenges. This paper (1)elucidates the problem of intersectionality in algorithmic fairness, (2) develops desiderata toclarify the challenges underlying the problem and guide the search for potential solutions,(3) illustrates the desiderata and potential solutions by sketching a proposal using simplehypothesis testing, and (4) evaluates, partly empirically, this proposal against the proposeddesiderata.
APA
Himmelreich, J., Hsu, A., Veomett, E. & Lum, K.. (2025). The Intersectionality Problem for Algorithmic Fairness. Proceedings of the Algorithmic Fairness Through the Lens of Metrics and Evaluation, in Proceedings of Machine Learning Research 279:68-95 Available from https://proceedings.mlr.press/v279/himmelreich25a.html.

Related Material