Trustworthy and Collaborative AI through Federated Learning

Speaker:  Li Xiong, Emory University.

Time:       14:00-15:00, May 23^th

Location: Room 1C 101, SIST

Host:        Wenjie Wang

Abstract:

Federated learning (FL) is a driving technology for collaborative AI which allows decentralized clients (e.g., edge devices or healthcare organizations) to collaboratively train machine learning models without directly sharing their data. I will present several of our recent works towards trustworthy FL including: 1) privacy-enhanced algorithms for ensuring personalized differential privacy while optimizing model utility, and 2) robust aggregation algorithms for addressing potentially malicious clients. I will discuss their applications in edge computing and healthcare with open directions. 

Bio:

Li Xiong is a Samuel Dobbs Professor of Computer Science and Biomedical Informatics at Emory University. She held a Winship Distinguished Research Professorship from 2015-2018. She has a Ph.D. from Georgia Institute of Technology, an MS from Johns Hopkins University, and a BS from the University of Science and Technology of China. She and her research lab, Assured Information Management and Sharing (AIMS), conduct research on the intersection of data management, machine learning, and data privacy and security. She is an IEEE fellow.  More details are at http://www. cs.emory.edu/~lxiong.