Machine learning, particularly distributed learning, stands as the cornerstone in the vision of future network intelligence, owing to its remarkable capability of addressing intricate computational tasks and modeling complexities. In this talk, we provide a comprehensive coverage of a distributed learning paradigm rooted in federated learning. Specifically, we start with a brief overview of federated learning, including the general architecture, model training algorithm, and analytical framework that quantifies the convergence rate. Then, we elucidate an over-the-air computation-based variant of federated learning, which circumvents the communication bottleneck by harnessing the superposition properties of wireless channels. Notably, such a scheme presents new advantages, such as reduced processing latency, enhanced privacy protection, and (potentially) better generalization power, demonstrating a possible harmony between wireless communication and distributed learning. We also discuss several approaches to personalize the federated learning framework in accordance with the end-users data distribution, addressing challenges stemming from data heterogeneity. In addition, we showcase a few applications of personalized federated learning in coping with massive random access problems, robustifying over-the-air federated learning, and enhancing the generalization performance with specifically devised communication protocols. Furthermore, we share some of our recent works investigating the interplay between federated learning and foundation models, as well as O-RAN frameworks, poised as versatile platforms that catalyze the practical deployment of foundational models in wireless edge networks.

Tony Q.S. Quek received the B.E. and M.E. degrees in Electrical and Electronics Engineering from Tokyo Institute of Technology, respectively. At Massachusetts Institute of Technology, he earned the Ph.D. in Electrical Engineering and Computer Science. Currently, he is the Cheng Tsang Man Chair Professor with Singapore University of Technology and Design (SUTD) and ST Engineering Distinguished Professor. He also serves as the Head of ISTD Pillar, Director for Future Communications R&D Programme, Sector Lead for SUTD AI Program, and the Deputy Director of SUTD-ZJU IDEA. His current research topics include wireless communications and networking, 6G, network intelligence, non-terrestrial networks, and open radio access network.

Dr. Quek has been actively involved in organizing and chairing sessions and has served as a TPC member in numerous international conferences. He is currently serving as an Area Editor for the IEEE Transactions on Wireless Communications. He was an Executive Editorial Committee Member of the IEEE Transactions on Wireless Communications, an Editor of the IEEE Transactions on Communications, and an Editor of the IEEE Wireless Communications Letters.

Dr. Quek received the 2008 Philip Yeo Prize for Outstanding Achievement in Research, the 2012 IEEE William R. Bennett Prize, the 2016 IEEE Signal Processing Society Young Author Best Paper Award, the 2017 CTTC Early Achievement Award, the 2017 IEEE ComSoc AP Outstanding Paper Award, the 2020 IEEE Communications Society Young Author Best Paper Award, the 2020 IEEE Stephen O. Rice Prize, the 2020 Nokia Visiting Professorship, and the the 2022 IEEE Signal Processing Society Best Paper Award. He is a Fellow of IEEE and a Fellow of the Academy of Engineering Singapore.