Keynote 1: Wednesday, November 29, 3 PM - 4 PM CET (Paris, Berlin time)
Jeffrey Andrews, University of Texas at Austin, USA
Session Chair: Khaled Letaief, The Hong Kong University of Science & Technology, HK.
Title: Unlocking new capacity in 6G cellular systems via site-specific ML-aided design
Abstract: A key enabling 6G technology will be deep learning, which can unlock previously hidden system-level gains, particularly by efficiently learning custom site-specific communication techniques that are optimally adapted for each cell-site. I will present a short summary of some of my group’s recent discoveries and technologies based on deep learning (DL) that demonstrate a large potential impact in 6G. The first is a novel and practical approach for beam alignment in millimeter wave and THz bands that can achieve a phenomenal speed up — at least 10x and in some cases approaching 1000x — by sensing and exploiting unique aspects of the environment. The second is a novel methodology for downlink precoding and uplink feedback for upper midband (7-15 GHz) spectrum, that can be used for both SU-MIMO and MU-MIMO. The UEs learn near-optimal feedback patterns and the BSs learn near-optimal precoders directly from that feedback. The technique is trained and tested using Nokia’s ray tracing based channel model for 7 GHz channels. The third is a site-specific multicell optimization that rapidly learns near-optimal global settings for each base stations antenna arrays, a problem that is completely intractable using conventional techniques. It is trained and tested on AT&T’s commercial simulation platform and shows at least 2x gain in both coverage and capacity metrics relative to typical settings.
Bio: Jeffrey Andrews is the Truchard Family Endowed Chair in Engineering at the University of Texas at Austin where is Director of 6G@UT. He received the B.S. in Engineering with High Distinction from Harvey Mudd College, and the M.S. and Ph.D. in Electrical Engineering from Stanford University. Dr. Andrews is an IEEE Fellow and ISI Highly Cited Researcher and has been co-recipient of 15 best paper awards as well as the 2015 Terman Award, the NSF CAREER Award, the 2021 Gordon Lepley Memorial Teaching Award, the 2021 IEEE ComSoc Joe LoCicero Service Award, the IEEE ComSoc Wireless Communications Technical Committee Recognition Award, and the 2019 IEEE Kiyo Tomiyasu technical field award. His former students include five IEEE Fellows, 12 professors at top universities in the USA, Asia, and Europe, and industry leaders on LTE and 5G systems, on which they collectively hold over one thousand US patents.
Keynote 2: Thursday, November 30, 3 PM - 4 PM CET (Paris, Berlin time)
Rose Hu, Utah State University, USA
Session Chair: Lajos Hanzo, Southampton University, UK
Title: Empowering Federated Learning: Tackling Challenges for Efficiency, Privacy, and Security in Decentralized and Collaborative Machine Learning
Abstract: Conventional centralized machine learning (ML) demands massive data collection for model training, often raising concerns about privacy and straining communication and computation resources. The rapid advancement of edge devices' computational capacity has paved the way for localized model training, reducing the reliance on remote servers. Federated Learning (FL) is a decentralized ML technique that empowers models to train locally on each client device. In FL, model parameters, not raw data, are shared among clients, thereby protecting user privacy while facilitating distributed collaboration. Nonetheless, FL faces many challenges, including data and computation heterogeneity, a large number of clients and substantial model dimensions, leading to issues on communication costs, model convergence, and security. This keynote talk will present the latest findings in our research aimed at addressing these FL challenges. Approaches to mitigate communication costs in wireless networks, tackle system heterogeneity, and enhance security and privacy will be discussed. Leveraging techniques such as advanced access technologies, model gradient compression, Asynchronous FL scheduling, and approximate communication, ML training can be expedited and wireless communication costs can be reduced. Furthermore, model update based (MUB) aggregation is exploited to defend against Byzantine attacks, and the individual client model initialization combined with MUB is used to enhance privacy protection in FL.
Bio: Rose Qingyang Hu is Professor with the Electrical and Computer Engineering Department and Associate Dean for research of College of Engineering at Utah State University. She also directs Communications Network Innovation Lab at Utah State University. Besides decades of academia research experience, she has more than 10 years industrial R&D experience with Nortel, Blackberry, and Intel as a technical manager, a senior research scientist, and a senior wireless system architect, actively participating in industrial 3G/4G technology development, standardization, system level simulation and performance evaluation. Her current research interests include next-generation wireless system design and optimization, Internet of Things, Cyber Physical system, Mobile Edge Computing, artificial intelligence in wireless networks. She has published over 300 in leading IEEE journals and conferences and also holds 30+ patents in her research areas. Rose Hu is an IEEE Fellow, IEEE Communications Society Distinguished Lecturer 2015-2018, IEEE Vehicular Technology Society Distinguished Lecturer 2020-2022, NIST Communication Technology Laboratory Innovator 2020, and a recipient of Best Paper Awards from the IEEE GLOBECOM 2012, the IEEE ICC 2015, the IEEE VTC Spring 2016, and the IEEE ICC 2016. She is currently serving as the IEEE ComSoc BoG Chief Information Officer and Associate Editor-In-Chief of IEEE Commutations Magazine. She is also serving on the editorial boards of the IEEE Transactions on Wireless Communications, IEEE Transactions on Vehicular Technology, and IEEE Wireless Communications.