{"id":33404,"date":"2024-05-21T15:44:46","date_gmt":"2024-05-21T13:44:46","guid":{"rendered":"https:\/\/www.l3s.de\/?p=33404"},"modified":"2024-06-11T11:30:46","modified_gmt":"2024-06-11T09:30:46","slug":"between-accuracy-and-fairness","status":"publish","type":"post","link":"https:\/\/www.l3s.de\/de\/between-accuracy-and-fairness\/","title":{"rendered":"Zwischen Genauigkeit und Fairness"},"content":{"rendered":"

L3S Best Publication of the Quarter (1\/2024<\/strong>)
Category: Fairness<\/strong><\/p>\n\n\n\n

FairTrade: Pareto-optimale Kompromisse zwischen ausgewogener Genauigkeit und Fairness beim f\u00f6derierten Lernen<\/strong><\/p>\n\n\n\n

Authors: Maryam Badar, Sandipan Sikdar, Wolfgang Nejdl and Marco Fisichella<\/p>\n\n\n\n

Presented at the 38th<\/sup> Annual AAAI Conference on Artificial Intelligence \u00a0(A* Conference)\u00a0<\/em>
https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/28971<\/a><\/p>\n\n\n\n

<\/div>\n\n\n\n

Welches Problem l\u00f6sen Sie mit Ihrer Forschung?<\/strong><\/p>\n\n\n\n

Die meisten modernen Methoden des fairen f\u00f6derierten Lernens geben die Genauigkeit als Ma\u00df f\u00fcr die Leistung an, was zu falschen Interpretationen der Wirksamkeit des Modells bei der Verringerung von Diskriminierung f\u00fchren kann. Unsere Arbeit zielt darauf ab, einen Pareto-optimalen Kompromiss zwischen ausgewogener Genauigkeit und Fairness in einer f\u00f6derierten Umgebung (FairTrade) zu erreichen.<\/p>\n\n\n\n

Was ist das Neue an Ihrer Forschung?<\/strong><\/p>\n\n\n\n

Unsere Arbeit ist der erste Versuch zur Anwendung der Mehrzieloptimierung, um das schwierige Gleichgewicht zwischen der ausgewogenen Genauigkeit des Modells und der Fairness auszuhandeln.<\/p>\n\n\n\n

\n\n\n\n

Badar, M., Sikdar, S., Nejdl, W., & Fisichella, M. (2024). FairTrade: Achieving Pareto-Optimal Trade-Offs between Balanced Accuracy and Fairness in Federated Learning. Proceedings of the AAAI Conference on Artificial Intelligence<\/em>, 38<\/em>(10), 10962-10970. https:\/\/doi.org\/10.1609\/aaai.v38i10.28971<\/a><\/p>","protected":false},"excerpt":{"rendered":"

The paper “FairTrade: Achieving Pareto-Optimal Trade-offs Between Balanced Accuracy and Fairness in Federated Learning” is the best L3S publication of the quarter in the category “Fairness”<\/p>","protected":false},"author":6,"featured_media":33498,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[161],"tags":[],"class_list":["post-33404","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-best-publications"],"acf":[],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t