T1: A Tale of Interference in Machine Learning Over-the-Air

Co-organizer: Howard H. Yang, Zhejiang University, China
Co-organizer: Zihan Chen, Singapore University of Technology and Design, Singapore
Co-organizer: Chenyuan Feng, EURECOM, France
Co-organizer: Tony Q. S. Quek, Singapore University of Technology and Design, Singapore

Abstract: This tutorial aims to present the current research efforts on implementing machine learning algorithms in wireless systems. Specifically, we provide a comprehensive coverage of a distributed learning paradigm based on over-the-air computing, a.k.a. over-the-air machine learning (OTA-ML). We will present the general architecture, model training algorithms, and an analytical framework that quantifies the convergence rate of OTA-ML. The analysis takes into account key effects from wireless transmissions, such as channel fading and interference, on the convergence performance. It discloses how interference is deteriorating the model training process. Then, we elaborate on several improvements to the OTA-ML from different aspects, e.g., using pruning techniques to reduce the computation and communication overheads, adopting adaptive optimization methods to accelerate the training, leveraging gradient clipping and model personalization to improve the robustness of the training, as well as how foundation models could be integrated into OTA-ML. Finally, we will elaborate on the analysis of generalization error of the statistical models trained by OTA-ML, which shows that wireless interference has the positive potential of improving the generalization capability. A few signal processing methods that exploit interference for a better generalization will also be discussed. We will conclude this tutorial by shedding light on future works.

Co-organizer’s Bios:

Howard H. Yang

Howard H. Yang received the Ph.D. degree in Electrical Engineering from the Singapore University of Technology and Design, Singapore, in 2017. Currently, he is an assistant professor with the ZJUUIUC Institute, Haining, China. He is also an adjunct assistant professor with the Electrical and Computer Engineering Department, University of Illinois Urbana-Champaign. His background also
features appointments at the University of Texas at Austin and Princeton University. He currently serves as an Associate Editor for the IEEE Transactions on Wireless Communications. He also serves as the Symposium Co-Chair of the IEEE International Conference on Communications in 2024. In addition, he has organized several workshops and special sessions relevant to distributed machine learning in conferences including IEEE ICASSP, IEEE SECON, IEEE SPAWC, and WiOpt. He received the IEEE Signal Processing Society Best Paper Award in 2022. His research interests cover various aspects of wireless communications, networking, and signal processing.

Zihan Chen

Zihan Chen received his Ph.D. degree from the Singapore University of Technology and Design-National University of Singapore Joint Ph.D. Program in 2022. Currently, he is an Associate Researcher Fellow at SUTD. His research mainly focuses on federated learning and network intelligence.

Chenyuan Feng

Chenyuan Feng received the Ph.D. degree in information system technology and design from Singapore University of Technology and Design (SUTD), Singapore in 2021. Currently, she is an
Associate Researcher Fellow at EURECOM, France. Her research interests include edge intelligence, federated learning and generative AI for future communication. She received the IEEE
ComComAp Best Paper Award in 2021, serves as an Editor for IEEE Internet of Things Journal and IEEE Open Journal of the Communications Society, and a Track-chair at 2024 IEEE International Conference on Communication Technology. She is a Marie Skłodowska-Curie scholar.

Tony Q. S. Quek

Tony Q. S. Quek received the B.E. and M.E. degrees in Electrical and Electronics Engineering from Tokyo Institute of Technology, Tokyo, Japan, respectively. At Massachusetts Institute of Technology
(MIT), Cambridge, MA, he earned the Ph.D. in Electrical Engineering and Computer Science. Currently, he is a tenured Professor with the Singapore University of Technology and Design (SUTD). He is also the Director of the Future Communications R&D Programme, the Head of ISTD Pillar, and the Deputy Director of the SUTD-ZJU IDEA, the 2020 Nokia Visiting Professor, and from 2016 to 2020, the Clarivate Analytics Highly Cited Researcher. His current research topics include wireless communications and networking, security, big data processing, network intelligence, and Internet of Things. He is an IEEE Fellow, a WWRF Fellow, and a Fellow of the Academy of Engineering Singapore