Bitte benutzen Sie diese Kennung, um auf die Ressource zu verweisen:
https://doi.org/10.21256/zhaw-21961| Publikationstyp: | Konferenz: Paper |
| Art der Begutachtung: | Peer review (Publikation) |
| Titel: | On the moral justification of statistical parity |
| Autor/-in: | Hertweck, Corinna Heitz, Christoph Loi, Michele |
| et. al: | No |
| DOI: | 10.1145/3442188.3445936 10.21256/zhaw-21961 |
| Tagungsband: | Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency |
| Seite(n): | 747 |
| Seiten bis: | 757 |
| Angaben zur Konferenz: | 4th ACM Conference on Fairness, Accountability, and Transparency (FAccT), online, 3-10 March 2021 |
| Erscheinungsdatum: | Mär-2021 |
| Verlag / Hrsg. Institution: | Association for Computing Machinery |
| Verlag / Hrsg. Institution: | New York |
| ISBN: | 978-1-4503-8309-7 |
| Sprache: | Englisch |
| Schlagwörter: | Fairness; Independence; Statistical parity; Distributive justice; Bias |
| Fachgebiet (DDC): | 005: Computerprogrammierung, Programme und Daten 170: Ethik |
| Zusammenfassung: | A crucial but often neglected aspect of algorithmic fairness is the question of how we justify enforcing a certain fairness metric from a moral perspective. When fairness metrics are proposed, they are typically argued for by highlighting their mathematical properties. Rarely are the moral assumptions beneath the metric explained. Our aim in this paper is to consider the moral aspects associated with the statistical fairness criterion of independence (statistical parity). To this end, we consider previous work, which discusses the two worldviews "What You See Is What You Get" (WYSIWYG) and "We're All Equal" (WAE) and by doing so provides some guidance for clarifying the possible assumptions in the design of algorithms. We present an extension of this work, which centers on morality. The most natural moral extension is that independence needs to be fulfilled if and only if differences in predictive features (e.g. high school grades and standardized test scores are predictive of performance at university) between socio-demographic groups are caused by unjust social disparities or measurement errors. Through two counterexamples, we demonstrate that this extension is not universally true. This means that the question of whether independence should be used or not cannot be satisfactorily answered by only considering the justness of differences in the predictive features. |
| Weitere Angaben: | The final publication is available in the ACM Digital Library via https://dl.acm.org/doi/10.1145/3442188.3445936. |
| URI: | https://digitalcollection.zhaw.ch/handle/11475/21961 |
| Volltext Version: | Akzeptierte Version |
| Lizenz (gemäss Verlagsvertrag): | Lizenz gemäss Verlagsvertrag |
| Departement: | School of Engineering |
| Organisationseinheit: | Institut für Datenanalyse und Prozessdesign (IDP) |
| Enthalten in den Sammlungen: | Publikationen School of Engineering |
Dateien zu dieser Ressource:
| Datei | Beschreibung | Größe | Format | |
|---|---|---|---|---|
| 2021_Hertweck-etal_Moral-Justification-of-Statistical-Parity.pdf | Accepted Version | 413 kB | Adobe PDF |  Öffnen/Anzeigen |
Zur Langanzeige
Hertweck, C., Heitz, C., & Loi, M. (2021). On the moral justification of statistical parity [Conference paper]. Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, 747–757. https://doi.org/10.1145/3442188.3445936
Hertweck, C., Heitz, C. and Loi, M. (2021) ‘On the moral justification of statistical parity’, in Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency. New York: Association for Computing Machinery, pp. 747–757. Available at: https://doi.org/10.1145/3442188.3445936.
C. Hertweck, C. Heitz, and M. Loi, “On the moral justification of statistical parity,” in Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, Mar. 2021, pp. 747–757. doi: 10.1145/3442188.3445936.
HERTWECK, Corinna, Christoph HEITZ und Michele LOI, 2021. On the moral justification of statistical parity. In: Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency. Conference paper. New York: Association for Computing Machinery. März 2021. S. 747–757. ISBN 978-1-4503-8309-7
Hertweck, Corinna, Christoph Heitz, and Michele Loi. 2021. “On the Moral Justification of Statistical Parity.” Conference paper. In Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, 747–57. New York: Association for Computing Machinery. https://doi.org/10.1145/3442188.3445936.
Hertweck, Corinna, et al. “On the Moral Justification of Statistical Parity.” Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, Association for Computing Machinery, 2021, pp. 747–57, https://doi.org/10.1145/3442188.3445936.
Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt, soweit nicht anderweitig angezeigt.