Wei Lin

Wei Lin

Auto-generated profile, based on publicly available information

Wei Lin

Chinese University of Hong Kong, Hong Kong, SAR, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 February 2022 in Reliability Engineering & System Safety
Verified
Journal Article
Closed access
SWSebastian Wandelt
Sebastian Wandelt
WLWei Lin
Wei Lin
Xiaoqian SunXiaoqian Sun
Xiaoqian Sun
Massimiliano ZaninMassimiliano Zanin
Massimiliano Zanin

11 February 2025 in IEEE Transactions on Cloud Computing
Verified
Journal Article
Closed access
KMKaiwei Mo
Kaiwei Mo
WLWei Lin
Wei Lin
JLJiaxun Lu
Jiaxun Lu
CXChun Jason Xue
Chun Jason Xue
YSYunfeng Shao
Yunfeng Shao
HXHong Xu
Hong Xu
Federated learning (FL) is increasingly adopted to combine knowledge from clients in training without revealing their private data. In order to improve the performance of different participants, personalized FL has recently been proposed. However, considering the non-independent and identically distributed (non-IID) data and limited bandwidth at clients, the model performance could be compromised. In reality, clients near each other often tend to have similar data distributions. In this work, we train the personalized edge-based model in the client-edge-server FL. While considering the differences in data distribution, we fully utilize the limited bandwidth resources. To make training efficient and accurate at the same time, An intuitive idea is to learn as much useful knowledge as possible from other edges and reduce the accuracy loss incurred by non-IID data. Therefore, we devise Grouping Hierarchical Personalized Federated Learning (GHPFL). In this framework, each edge establishes physical connections with multiple clients, while the server physically connects with edges. It clusters edges into groups and establishes client-edge logical connections for synchronization. This is based on data similarities that the nodes actively identify, as well as the underlying physical topology. We perform a large-scale evaluation to demonstrate GHPFL's benefits over other schemes.