Wei Lin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Wei Lin has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Chun Jason Xue
Mohamed bin Zayed University of Artificial Intelligence
1 shared publication - Hong Xu
The Chinese University of Hong Kong, Hong Kong, China
1 shared publication - Jiaxun Lu
Tsinghua National Laboratory for Information Science and Technology Department of Electronic Engineering State Key Laboratory on Microwave and Digital Communications Tsinghua University Beijing China
1 shared publication - Kaiwei Mo
City University of Hong Kong, Hong Kong, SAR, China
1 shared publication - Massimiliano Zanin
Instituto de Fisica Interdisciplinar y Sistemas Complejos IFISC (CSIC-UIB), SPAIN
1 shared publication Sebastian Wandelt
1 shared publication
Latest Publications
- 11 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cloud Computing
- Vol. 13 (2) , 473-484
GHPFL: Advancing Personalized Edge-Based Learning Through Optimized Bandwidth Utilization
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.
- 11 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cloud Computing
- Vol. 13 (2) , 473-484
GHPFL: Advancing Personalized Edge-Based Learning Through Optimized Bandwidth Utilization
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.
- 1 February 2022
- Published by Elsevier in Reliability Engineering & System Safety
- Vol. 218
From random failures to targeted attacks in network dismantling
- 1 February 2022
- Published by Elsevier in Reliability Engineering & System Safety
- Vol. 218
From random failures to targeted attacks in network dismantling