Kolloquium SoSe 2022
Dr. Meike Zehlike
Zalando SE Berlin
When: Mo, 13.06.2022, at 17:15
Where: Konrad-Zuse-Hörsaal (Room B-201)
We are going to provide a livestream during the lecture. For the access data please register at https://mail-mm01.rrz.uni-hamburg.de/mailman/listinfo/kolloquium.
Fairness in Rankings
This work contributes the following to solve the aforementioned problems, which I will cover in-depth in the talk:
Five Classification Contexts of Fairness: We identify the fairness properties of all important fairness definitions, including the ones we newly introduce, by relating them to different philosophical understandings of fairness. We introduce five concepts, by which we classify all works that we present in this work.
Fair Ranking Methods: We present two group-fairness-based frameworks, an in-processing, exposure-based approach, and a post-processing, probabilistic approach.
An Open-Source API: We implement our new fairness frameworks into the first open-source library for fairness in ranked search results, as a stand-alone programming library in Python and Java, as well as a plugin for the widely known search-engine “Elasticsearch”.
Meike Zehlike is a Senior Applied Scientist at Zalando Research in the Algorithmic Privacy and Fairness team, and an ethical AI consultant. She earned her Ph.D. in computer science at Humboldt Universität zu Berlin in 2022, working under Ulf Leser (HU), Carlos Castillo (UPF Barcelona), and Krishna Gummadi (MPI-SWS Saarbrücken).
She received a prestigious PhD research grant from the Data Transparency Lab in 2017 and several awards such as the Google Women Techmaker Award in 2019. Her research interests center around artificial intelligence and its social impact, automatic discrimination discovery and algorithmic fairness, as well as the use of artificial intelligence in medical applications.