Hacker P, Wiedemann E, Zehlike M (2020)
Publication Type: Conference contribution
Publication year: 2020
Publisher: Gesellschaft fur Informatik (GI)
Book Volume: P-307
Pages Range: 99-108
Conference Proceedings Title: Lecture Notes in Informatics (LNI), Proceedings - Series of the Gesellschaft fur Informatik (GI)
Event location: Karlsruhe, DEU
ISBN: 9783885797012
DOI: 10.18420/inf2020_09
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.
APA:
Hacker, P., Wiedemann, E., & Zehlike, M. (2020). Towards a Flexible Framework for Algorithmic Fairness. In Ralf H. Reussner, Anne Koziolek, Robert Heinrich (Eds.), Lecture Notes in Informatics (LNI), Proceedings - Series of the Gesellschaft fur Informatik (GI) (pp. 99-108). Karlsruhe, DEU: Gesellschaft fur Informatik (GI).
MLA:
Hacker, Philipp, Emil Wiedemann, and Meike Zehlike. "Towards a Flexible Framework for Algorithmic Fairness." Proceedings of the 50. Jahrestagung der Gesellschaft fur Informatik, INFORMATIK 2020 - 50th Annual Conference of the German Informatics Society, INFORMATIK 2020, Karlsruhe, DEU Ed. Ralf H. Reussner, Anne Koziolek, Robert Heinrich, Gesellschaft fur Informatik (GI), 2020. 99-108.
BibTeX: Download