The Intersectionality Problem for Algorithmic Fairness
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909392328196096 |
|---|---|
| author | Himmelreich, Johannes Hsu, Arbie Lum, Kristian Veomett, Ellen |
| author_facet | Himmelreich, Johannes Hsu, Arbie Lum, Kristian Veomett, Ellen |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_02569 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | The Intersectionality Problem for Algorithmic Fairness Himmelreich, Johannes Hsu, Arbie Lum, Kristian Veomett, Ellen Machine Learning Artificial Intelligence Computers and Society 68T37, 60H30, 68W40 I.6.4; I.5.2 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. |
| title | The Intersectionality Problem for Algorithmic Fairness |
| topic | Machine Learning Artificial Intelligence Computers and Society 68T37, 60H30, 68W40 I.6.4; I.5.2 |
| url | https://arxiv.org/abs/2411.02569 |