The 12th International Conference on Electronics, Communications and Networks
(CECNet 2022)

Abstract: Federated learning (FL) has been recognized as a viable distributed learning paradigm which trains a machine learning model collaboratively with massive mobile devices in the wireless edge while protecting user privacy. Although various communication schemes have been proposed to expedite the FL process, most of them have assumed ideal wireless channels which provide reliable and lossless communication links between the server and mobile clients. Unfortunately, in practical systems with limited radio resources such as constraint on the training latency and constraints on the transmission power and bandwidth, transmission of a large number of model parameters inevitably suffers from quantization errors (QE) and transmission outage (TO). In this talk, we consider such non-ideal wireless channels, and carry out the first analysis showing that the FL convergence can be severely jeopardized by TO and QE, but intriguingly can be alleviated if the clients have uniform outage probabilities. These insightful results motivate us to propose a robust FL scheme, named FedTOE, which performs joint allocation of wireless resources and quantization bits across the clients to minimize the QE while making the clients have the same TO probability. Extensive experimental results are presented to show the superior performance of FedTOE for deep learning-based classification tasks with transmission latency constraints.

Biography: Tsung-Hui Chang received the B.S. degree in electrical engineering and the Ph.D. degree in communications engineering from the National Tsing Hua University (NTHU), Hsinchu, Taiwan, in 2003 and 2008, respectively. He currently is an Associate Professor of the School of Science and Engineering (SSE), The Chinese University of Hong Kong, Shenzhen (CUHKSZ), China. Prior to being a faculty member, he held research positions with NTHU, from 2008 to 2011, and the University of California, Davis, CA, USA, from 2011 to 2012. His research interests include signal processing and optimization problems in data communications, machine learning and big data analysis.
Dr. Chang is an Elected Member of IEEE Signal Processing Society (SPS) Signal Processing for Communications and Networking Technical Committee (SPCOM TC), the Founding Chair of IEEE SPS Integrated Sensing and Communciation Technical Working Group (ISAC TWG), and the IEEE SPS Regional Director-at-Large of Region 10. He has served the editorial board for major SP journals, including an Associate Editor (2014/08-2018/12) and Senior Area Editor (2021/02-present) of IEEE Transactions on Signal Processing, and an Associate Editor of IEEE Transactions on Signal and Information Processing over Networks (2015/01-2018/12) and IEEE Open Journal of Signal Processing (2020/01-present). Dr. Chang received the Young Scholar Research Award of National Taiwan University of Science and Technology in 2014, IEEE ComSoc Asian-Pacific Outstanding Young Researcher Award in 2015, the Outstanding Faculty Research Award of SSE, CUHKSZ, in 2021, and the IEEE SPS Best Paper Awards in 2018 and 2021.