The University of Illinois at Urbana-Champaign
Year in School
REU Faculty Mentor
Research Area Interest
Fairness in contrastive learning on graphs
Biography & Research Abstract
Our research aims to find and set fairness constraints on existing state-of-the-art contrastive learning methods on graphs. Graphs are one kind of input for ML problems, and they can express complex relationships such as using nodes to represent each individual and edges to represent their relationship. As one subtopic of unsupervised learning, contrastive learning, is getting more and more popular in recent years. However, ethnic issues like fairness are overlooked by most existing CL methods, and only a few research touches on the fairness of CL. To solve this problem, we would like to explore a novel method by adding some constraints to existing state-of-the-art contrastive learning methods.
My name is Jade Xu, and I am a rising senior majoring in Statistics and Computer Science. My research interests include fair graph mining, contrastive learning, machine learning, and artificial intelligence. But I am also happy to try new areas and topics. This summer, I am working with graduate mentor Jian Kang and Professor Hanghang Tong about fairness-aware contrastive learning on graphs.