Title: Federated Learning With Efficiency and Privacy Considerations in Wireless Networks
Abstract: Centralized data collection and training in conventional machine learning (ML) algorithms have raised many concerns including privacy restrictions and communication cost due to massive amount of data transfer. Federated leaning (FL) exploits the rapidly growing computational capacity in small local devices and allows these devices to train ML models locally and only exchange the trained model parameters with the edge server. Through this, FL can greatly alleviate data privacy concern, reduce communication cost, and help build a scalable centralized ML model. FL methods offer a number of prominent advantages, including scalability and data privacy. On the other hand, a large-scale wireless network normally involves many heterogeneous devices with varying constraints and encounters very dynamic channel environments. This raises many challenges such as system heterogeneity, statistical heterogeneity, privacy and security, user scheduling, fairness in FL. This talk will present some of our recent research outcomes on model parameter transmission schemes and user scheduling strategies in FL that tackle these challenges. Techniques such as NOMA and over-the-air computation are introduced to achieve fast ML training. Model parameter compression and sparsification are further introduced to reduce the wireless communication cost. Moreover, model update-based aggregation is applied to defend against Byzantine attacks and individual client model initialization schemes are exploited 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.