SPS-DSI (DEGAS) Webinar: Demystifying and Mitigating Unfairness for Learning over Graphs

Date: 22 January 2025
Time: 10:00 AM ET (New York time)
Presenter(s): Yanning Shen

DEGAS Webinar Series is an event initiated by the Data Science Initiative (DSI) of the IEEE Signal Processing (SP) Society. The goal is to provide the SP community with updates and advances in learning and inference on graphs. Signal processing and machine learning often deal with data living in regular domains such as space and time. This webinar series will cover the extension of these methods to network data, including topics such as graph filtering, graph sampling, spectral analysis of network data, graph topology identification, geometric deep learning, and so on. Applications can for instance be found in image processing, social networks, epidemics, wireless communications, brain science, recommender systems, and sensor networks. These bi-weekly webinars will be hosted on Zoom, with recordings made available in the IEEE Signal Processing Society’s YouTube channel following the live events. Further details about live and streaming access will follow. Each webinar speaker will give a lecture, which is followed by Q&A and discussions.

Abstract

We live in an era of big data and ‘‘small world’’, where a large amount of data resides on inter-connected graphs representing a wide range of physical and social interdependencies, e.g., smart grids and social networks. Hence, machine learning (ML) over graphs has attracted significant attention and has shown promising success in various applications. Despite this 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. To this end, this talk will introduce novel fairness-aware graph neural network (GNN) designs to address unfairness issues in learning over graphs. Furthermore, theoretical understandings are provided to explain the potential source of unfairness in GNNs and prove the efficacy of the proposed schemes. Experimental results on real networks are presented to demonstrate that the proposed framework can enhance fairness while providing comparable accuracy to state-of-the-art alternative approaches for node classification and link prediction tasks.

Biography

Renjie Liao

Yanning Shen received the Ph.D. degree from the University of Minnesota in 2019. She is an assistant professor with the EECS department at the University of California, Irvine. Her research interests span the areas of machine learning, network science, and data science.

Dr. Shen was selected as a Rising Star in EECS by Stanford University in 2017. She received the Microsoft Academic Grant Award for AI Research in 2021, the Google Research Scholar Award in the area of Machine Learning and Data Mining in 2022, the Hellman Fellowship in 2022, and the UCI Newkirk faculty fellowship in 2023. She is also an honoree of the MIT Technology Review 35 Innovators under 35 Asia Pacific in 2022. More detailed information can be found at her website.