Wanning Pan

Wanning Pan

Auto-generated profile, based on publicly available information

Wanning Pan

National Engineering Research Center for Big Data Technology and System, Service Computing Technology and System Lab, Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
15 September 2023 in IEEE Transactions on Computers
Verified
Journal Article
Closed access
DYDezhong Yao
Dezhong Yao
WPWanning Pan
Wanning Pan
YDYutong Dai
Yutong Dai
YWYao Wan
Yao Wan
XDXiaofeng Ding
Xiaofeng Ding
Lichao SunLichao Sun
Lichao Sun
Federated learning, as one enabling technology of edge intelligence, has gained substantial attention due to its efficacy in training deep learning models without data privacy and network bandwidth concerns. However, due to the heterogeneity of the edge computing system and data, many methods suffer from the “ client-drift ” issue that could considerably impede the convergence of global model training: local models on clients can drift apart, and the aggregated model can be different from the global optimum. To tackle this issue, one intuitive idea is to guide the local model training by global teachers, i.e. , past global models, where each client learns the global knowledge from past global models via adaptive knowledge distillation techniques. Inspired by these insights, we propose a novel approach for heterogeneous federated learning, F ed GKD, which fuses the knowledge from historical global models and guides local training to alleviate the “ client-drift ” issue. In this paper, we evaluate F ed GKD through extensive experiments across various CV and NLP datasets (i.e., CIFAR-10/100, Tiny-ImageNet, AG News, SST5) under different heterogeneous settings. The proposed method is guaranteed to converge under common assumptions and outperforms the state-of-the-art baselines in the non-IID federated setting.

25 April 2025 in Artificial Intelligence
Verified
Journal Article
Open access
DYDezhong Yao
Dezhong Yao
WPWanning Pan
Wanning Pan
YSYuexin Shi
Yuexin Shi
MOMichael J. O'NEill
Michael J. O'NEill
YDYutong Dai
Yutong Dai
Lichao SunLichao Sun
Lichao Sun