IoT Thrust Seminar | Distributed Learning in Heterogeneous Wireless Networks
Supporting the below United Nations Sustainable Development Goals:支持以下聯合國可持續發展目標：支持以下联合国可持续发展目标：
Distributed learning techniques can efficiently support training machine learning models by exploiting the distributed computational resources in wireless networks. In this talk, distributed learning in heterogeneous wireless networks will be discussed, with focus on the most recent distributed learning approaches. Considering the diversity of wireless users in terms of different communication, computational and data resources, implementing distributed learning techniques in wireless networks is challenging. This talk starts from a comprehensive overview of the state-of-art distributed learning architectures in wireless communications. Then recent work on designing new hybrid distributed learning architectures and user scheduling schemes to address the challenges of diverse users in wireless networks is introduced. Moreover, energy-efficient user scheduling to improve energy and computation efficiency of wireless users will also be discussed.
Dr. Xiaolan Liu is a lecturer (Assistant Professor) at the Institute of Digital Technologies at Loughborough University in the London campus. She is also a visiting research scholar at King’s College London (KCL) and The Hong Kong University of Science and Technology (HKUST). She received her PhD degree in Computer Science from Queen Mary University of London (QMUL) in July 2021. Her current research interests include distributed learning for wireless communications, reinforcement learning in edge computing, and privacy-preserving machine learning. She has published more than 30 Journal and Conference papers in these areas with the H-index of 15. She was a research associate in KCL from August 2020 to July 2021. She is the editor for IEEE Wireless Communication Letters, IEEE Journal Internet of Things, and China Communications, she serves as the symposium chair for IEEE conferences ICC 2025.