一、讲座安排

 1.讲座时间：2025年12月23日9:30-11:00

 2.讲座地点：海角社区 南湖校区一教304

二、主讲内容

题目:Distributed learning in heterogeneous wireless networks & Trustworthy Federated Learning

摘要：Distributed learning techniques play an important role in supporting advanced network edge applications, by exploiting the distributed computational resources and their privacy-preserving properties. However, the diversity of wireless users in terms of different communication, computational and data resources, implementing distributed learning techniques in wireless networks is challenging. Moreover, the malicious users, during training, can systematically create malicious model parameters to compromise the models’ predictive and generative capabilities, resulting in high uncertainty about their reliability. In this talk, distributed learning in heterogeneous wireless networks will be discussed, with focus on hybrid learning architectures and user scheduling schemes. Then, a Bayesian Optimization based model poisoning attack method which aims to maximise the uncertainty of the global model output will be introduced.

主讲人：刘小兰

Dr. Xiaolan Liu is an Assistant Professor in Smart Internet Lab at University of Bristol since 2024. She was an Assistant Professor at Loughborough University from 2021 to 2024. 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 sensing-aided communication, 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 24. She was a research associate in KCL from August 2020 to July 2021. She serves as the editor for IEEE Wireless Communication Letters and IEEE Network Magazines, and the symposium chair for IEEE ICC 2025.  

欢迎广大师生积极参与！