The Intersectionality Problem for Algorithmic Fairness
It addresses a critical gap in ensuring fairness for marginalized subgroups in AI systems, though the approach appears incremental.
The paper tackles the challenge of achieving and verifying algorithmic fairness across intersectional groups, which are often small, by developing desiderata and evaluating a hypothesis testing proposal against them.
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.