Speaker: Xiaorui Liu, Ph.D. candidate in the Department of Computer Science and Engineering at Michigan State University
Title: Efficient and Secure Machine Learning with Message Passing
Abstract: Message passing is the essential building block in many machine learning problems such as distributed machine learning and geometric deep learning. In this talk, I will introduce several innovative designs of message passing schemes that address the efficiency and security issues in machine learning. Specifically, first I will present novel distributed algorithms with compressed message passing that enable large-scale, efficient, and scalable distributed machine learning on big data. Then I will show how to significantly improve the security and robustness of machine learning predictions by exploiting the structural information in data by novel message passing designs.
Bio: Xiaorui Liu is a Ph.D. candidate in the Department of Computer Science and Engineering at Michigan State University. His advisor is Prof. Jiliang Tang. His research interests include distributed and trustworthy machine learning, with a focus on big data and graph data. He was awarded the Best Paper Honorable Mention Award at ICHI 2019, MSU Engineering Distinguished Fellowship, and Cloud Computing Fellowship. He organized and co-presented four tutorials in KDD2021, IJCAI2021, and ICAPS2021, and he has published innovative works in top-tier conferences such as NeurIPS, ICML, ICLR, KDD, and AISTATS. More information can be found on his homepage https://cse.msu.edu/~xiaorui/