FedHDE: an efficient federated learning model based on hyper-knowledge distillation
Journal of King Saud University Computer and Information Sciences · 2026-05 · 38 (4)
DOI: 10.1007/s44443-026-00503-1 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of King Saud University Computer and Information Sciences, online erschienen am 13.02.2026. Verfasst von Xingang Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Scientific Research Projects of Colleges and Universities in Henan Province of China, Natural Science Foundation of Henan, Philosophy and Social Sciences Research Planning Program of Henan Province.
Abstract (Originalsprache)
The heterogeneity of data between different clients limits the performance of federated learning training, and hyper-knowledge distillation has emerged as a potential solution to address heterogeneous data. However, existing hyper-knowledge distillation methods often sacrifice efficiency to improve model performance. To address these challenges, this paper proposes FedHDE, a novel federated learning framework based on hyper-knowledge distillation and efficient tensor optimization. FedHDE integrates a Dynamic Client Selection strategy within a teacher–assistant–student hierarchical structure to enhance global aggregation accuracy and reliability without relying on public datasets or server-side models. Furthermore, an efficient tensor optimization algorithm is introduced to improve numerical stability and reduce computation time. Theoretical analysis demonstrates that FedHDE achieves a convergence rate of $$O(1/\sqrt{T})$$ O ( 1 / T ) , ensuring efficient and stable learning. Experimental results on the CIFAR10 dataset show that FedHDE improves both local and global accuracy by 0.14%–4.32%, while reducing training time by 65.28% compared to state-of-the-art baselines.Code is public at https://anonymous.4open.science/r/FedHDE .
Förderung
- Key Scientific Research Projects of Colleges and Universities in Henan Province of China
- Natural Science Foundation of Henan
- Philosophy and Social Sciences Research Planning Program of Henan Province
- Scientific Research Project on the Development of Educational Informatization
- the General Project of Ministry of Education Foundation on Humanities and Social Sciences
- Training Plan for Young Backbone Teachers in Higher Education Institutions in Henan Province
Zitieren
APA
Zhang, X., Liu, C., Shao, X., Li, T., Li, H., & Zhang, D. (2026). FedHDE: an efficient federated learning model based on hyper-knowledge distillation. Journal of King Saud University Computer and Information Sciences, 38(4). https://doi.org/10.1007/s44443-026-00503-1
Vancouver
Zhang X, Liu C, Shao X, Li T, Li H, Zhang D. FedHDE: an efficient federated learning model based on hyper-knowledge distillation. Journal of King Saud University Computer and Information Sciences. 2026;38(4). doi:10.1007/s44443-026-00503-1
BibTeX
@article{Zhang2026,
author = {Zhang, Xingang and Liu, Chuang and Shao, Xiaofan and Li, Tingzhi and Li, He and Zhang, Dongyan},
title = {FedHDE: an efficient federated learning model based on hyper-knowledge distillation},
journal = {Journal of King Saud University Computer and Information Sciences},
year = {2026},
volume = {38},
number = {4},
doi = {10.1007/s44443-026-00503-1}
}
EUVIMED