- This event has passed.
Federated Learning in Resource Limited Wireless Networks
Thursday, August 1, 2024 @ 11:00 AM - 12:00 PM
Federated learning (FL) is an efficient and privacy-preserving distributed learning paradigm that enables massive edge devices to train machine learning models collaboratively. Although various communication schemes and algorithm designs have been proposed to expedite the FL process in resource-limited wireless networks, the unreliable nature of wireless channels, device heterogeneity, and data heterogeneity are still less explored. In this talk, number of solutions solutions will be discussed for addressing the above practical challenges in wireless FL. Firstly, to tackle the unreliable wireless channels, a novel FL framework, namely FL with gradient recycling (FL-GR), which recycles the historical gradients of unscheduled and transmission-failure devices to improve the learning performance of FL will be discussed. Secondly, to solve the heterogeneity issues, partial model aggregation, knowledge aided learning and adaptive model pruning-based FL framework will be explained. Based on our research experience, some open problems of wireless FL will be provided. Speaker(s): Professor Arumugam , Room: 460, Bldg: ENG, 245 Church Street, Toronto, Ontario, Canada, M5B 1Z4