Fairness-Aware learning over Graphs

Title: Fairness-Aware learning over Graphs

Speaker: Oyku Deniz Kose

Date and Time: Tuesday, April 2nd, 12:00pm

Location: EH 2430

Abstract:

Graphs are powerful mathematical tools that can represent complex real-world systems, such as financial markets and social networks, and the relations within them. Due to this, machine learning (ML) over graphs has attracted significant attention recently, and showed promising success in various applications. Despite the success, the large-scale deployment of graph-based ML algorithms in real-world systems relies heavily on how socially responsible they are. While graph-based ML models nicely integrate the nodal data with the connectivity, they also inherit potential unfairness. Using such ML models may therefore result in inevitable unfair results in various decision- and policy-making in the related applications. While fairness and explainability have attracted increasing attention in responsible ML, they are mostly under-explored in the graph domain. Motivated by this, in this talk, we first focus on the analysis of sources of bias in graph-based learning and then present fairness-aware learning algorithms that combat the identified bias sources. In addition, we will talk about certain real-word challenges that need to be considered in addition to fairness, e.g., efficiency, convergences.

Biography:

Oyku Deniz Kose received the B.S. and M.S. degrees in electrical and electronics engineering from Bogazici University, Istanbul, Turkey, in 2017 and 2020, respectively. She is currently working towards a Ph.D. degree with the Department of Electrical Engineering and Computer Science, University of California Irvine, Irvine, CA, USA. She received the Samueli Endowed Fellowship in 2021 and was a research intern at Google in 2023. Her research mainly focuses on trustworthy machine learning with a specific interest in graph-based learning.