August 19, 2021
Friday, August 27 12:30 – 1:30 pm CT on Webex
Federated Learning over Massive Wireless Networks
Chun-Hung Liu | firstname.lastname@example.org
Abstract: Federated learning (FL) over wireless networks is a distributed learning technique between a server and wireless clients without raw data delivery and thereby it is able to reduce network congestion, power consumption, latency, and security problems. The existing federated learning models possess two intrinsic issues that impede them to be practically implemented in massive wireless networks. One is the incapability of achieving effective learning from large amount of data distributed over massive wireless networks with limited radio and backhaul resources, and the other is the lack of robustness to data delivery outage. Accordingly, there is an imperative need to devise a new federated leaning model that is not affected by the two intrinsic issues and suitable for massive wireless networks. In this talk, a new FL model for large-scale wireless networks will be introduced. It not only leverages the limited network resources to fully exploit the advantage of real-time big data in the network, but also significantly mitigates the high risk of unreliable wireless transmission. This talk will also introduce how to apply the proposed FL model to some specific massive wireless systems and demonstrate some numerical results to validate the performances of the proposed FL model.
Biographical info: Dr. Liu received a B.S. in Electrical and Mechanical Engineering from National Taiwan University, an M.S. in Mechanical Engineering from MIT, and a Ph.D. degree in Electrical and Computer Engineering from the University of Texas at Austin. He is currently an assistant professor in the department of Electrical and Computer Engineering at Mississippi State University. Prior to joining MSU in 2018, he was with University of Michigan, National Chiao Tung University in Taiwan, and Qualcomm R&D in San Diego, CA. His research interests include wireless communication, information theory, machine learning, and data science. He was a recipient of the Best Paper Award from IEEE Globecom in 2008 and 2014.
*For further information, contact Dr. Jenny Du | email@example.com | 5-2035
For Webex Information, Scan the QR Code
To learn more about Dr. Liu’s research, visit his website – https://my.ece.msstate.edu/faculty/chliu/
The Department of Electrical and Computer Engineering at Mississippi State University consists of 23 faculty members (including 7 endowed professors), 3 clinical faculty, 10 professional and support staff, and over 700 undergraduate and graduate students with approximately 88 being at the Ph.D. level. With research expenditure of the department in excess of $10M, the department houses the largest High Voltage Laboratory among North American Universities. For more detailed information on the department please visit our website www.ece.msstate.edu.