Towards a Flexible Framework for Algorithmic Fairness
| dc.contributor.author | Hacker, Philipp | |
| dc.contributor.author | Wiedemann, Emil | |
| dc.contributor.author | Zehlike, Meike | |
| dc.contributor.editor | Reussner, Ralf H. | |
| dc.contributor.editor | Koziolek, Anne | |
| dc.contributor.editor | Heinrich, Robert | |
| dc.date.accessioned | 2021-01-27T13:34:34Z | |
| dc.date.available | 2021-01-27T13:34:34Z | |
| dc.date.issued | 2021 | |
| dc.description.abstract | Increasingly, scholars seek to integrate legal and technological insights to combat bias in AI systems. In recent years, many different definitions for ensuring non-discrimination in algorithmic decision systems have been put forward. In this paper, we first briefly describe the EU law framework covering cases of algorithmic discrimination. Second, we present an algorithm that harnesses optimal transport to provide a flexible framework to interpolate between different fairness definitions. Third, we show that important normative and legal challenges remain for the implementation of algorithmic fairness interventions in real-world scenarios. Overall, the paper seeks to contribute to the quest for flexible technical frameworks that can be adapted to varying legal and normative fairness constraints. | en |
| dc.identifier.doi | 10.18420/inf2020_09 | |
| dc.identifier.isbn | 978-3-88579-701-2 | |
| dc.identifier.pissn | 1617-5468 | |
| dc.identifier.uri | https://dl.gi.de/handle/20.500.12116/34803 | |
| dc.language.iso | en | |
| dc.publisher | Gesellschaft für Informatik, Bonn | |
| dc.relation.ispartof | INFORMATIK 2020 | |
| dc.relation.ispartofseries | Lecture Notes in Informatics (LNI) - Proceedings, Volume P-307 | |
| dc.subject | algorithmic fairness | |
| dc.subject | optimal transport | |
| dc.subject | discrimination | |
| dc.subject | algorithmic affirmative action | |
| dc.subject | EU law | |
| dc.title | Towards a Flexible Framework for Algorithmic Fairness | en |
| gi.citation.endPage | 108 | |
| gi.citation.startPage | 99 | |
| gi.conference.date | 28. September - 2. Oktober 2020 | |
| gi.conference.location | Karlsruhe | |
| gi.conference.sessiontitle | Ethik und KI |
Dateien
Originalbündel
1 - 1 von 1
Vorschaubild nicht verfügbar
- Name:
- A13-1.pdf
- Größe:
- 120.42 KB
- Format:
- Adobe Portable Document Format