Wireless innovations Next-generation
Online Workshop(WiNOW)
3-6 November, 2025 // Virtual
Mengyuan Zhang
Beihang University
Mengyuan Zhang is currently an Associate Professor with Beihang University, Beijing, China. He received the Ph.D. degree in Control Science and Engineering from Zhejiang University, Hangzhou, China, in 2020. And he received the M.S. degree from University of New South Wales, Sydney, NSW, Australia, in 2012. From 2020 to 2023, he worked as a Senior Algorithm Engineer at DAMO Academy of Alibaba Group, Hangzhou, China. He received the Best Paper Award at IEEE ICCC 2024 and served as the Symposium Co-Chair for the IEEE WCSP 2024. His current research interests include AI empowered protocol design and privacy protection in Space-Air-Ground-Integrated Networks and 6G Networks
Talk Title: Communication-Efficient Federated LoRA with Differential Privacy
Federated LoRA with pre-trained foundation models faces two major challenges: high communication overhead due to large-scale parameter transmission and potential privacy leakage from shared model parameters. This talk introduces a new federated LoRA framework that enhances communication efficiency and ensures differential privacy for participating clients.