Logo des Repositoriums
 

The Effect of Adversarial Debiasing on Model Performance

Kurzanzeige
dc.contributor.authorGötte, Gesa
dc.contributor.editorKlein, Maike
dc.contributor.editorKrupka, Daniel
dc.contributor.editorWinter, Cornelia
dc.contributor.editorWohlgemuth, Volker
dc.date.accessioned2023-11-29T14:50:17Z
dc.date.available2023-11-29T14:50:17Z
dc.date.issued2023
dc.description.abstractThis paper explores the effect of adversarial debiasing on the performance of machine learning models. As concerns about fairness in algorithmic decision-making grow, techniques for detecting and mitigating biases in ML models have been developed. However, there is a trade-off between fairness and model performance. This study investigates the impact of using adversarial debiasing on model performance in different scenarios of potential sampling biases and target distributions. Simulated data with varying structural and sampling parameters is used to evaluate the models’ performance. The results show that while adversarial debiasing can lead to significant improvements in certain scenarios, it can also result in impairments or no significant difference in performance compared to the normal models.en
dc.identifier.doi10.18420/inf2023_01
dc.identifier.isbn978-3-88579-731-9
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/43018
dc.language.isoen
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofINFORMATIK 2023 - Designing Futures: Zukünfte gestalten
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-337
dc.subjectFair AI
dc.subjectDebiasing
dc.titleThe Effect of Adversarial Debiasing on Model Performanceen
dc.typeText/Conference Paper
gi.citation.endPage44
gi.citation.publisherPlaceBonn
gi.citation.startPage39
gi.conference.date26.-29. September 2023
gi.conference.locationBerlin
gi.conference.sessiontitleYoung Scientists and early-stage research in Data Science Workshop (YSDS-23)

Dateien

Originalbündel
1 - 1 von 1
Vorschaubild nicht verfügbar
Name:
01_02_Goette.pdf
Größe:
218.21 KB
Format:
Adobe Portable Document Format
Herunterladen

Sammlungen

P337 - INFORMATIK 2023 - Designing Futures: Zukünfte gestalten