Edge-End Heterogeneous Collaborative Learning by Prototype Selection and Edge Association
IEEE Transactions on Parallel and Distributed Systems · 2026-07 · 37 (7) · 1485-1502
DOI: 10.1109/tpds.2026.3678282 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Parallel and Distributed Systems, 2026-07. Verfasst von Enze Yu und 9 weiteren Autor:innen. Die Arbeit nennt 61 Literaturangaben. Gefördert von: National Key R&D Program of China, Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
Edge-end collaborative learning trains models with exchanged knowledge through distributed interaction, alleviating the cloud’s burden. Edge-end heterogeneous collaborative learning further enables edge servers and end devices to train models of different scales in parallel based on their computational capabilities. This technology supports various applications in different resource conditions and improves server resource utilization. However, implementing it is challenging due to heavy communication costs and high global costs (time and energy). To this end, this paper proposes a novel prototype-based edge-end heterogeneous collaborative learning method and an optimization algorithm, which improves model performance and reduces training costs. We first use prototypes to perform collaborative learning and analyze the convergence. Prototypes are computed as mean feature vectors from different classes. The aggregated prototypes help capture class information on end devices and generate data on edge servers. Then, we study how to determine prototype selection and edge association to minimize training time, energy consumption, and prototype approximation error under a limited reward budget, which is proven to be NP-hard. We split the original problem into two subproblems. The first is solved in the closed form. Through approximation and reformulation, the second is transformed into a submodular maximization problem with knapsack and matroid constraints. On this basis, we propose an approximation algorithm with a theoretical guarantee. Finally, by simulation and field experiments, our method takes 3.61% of communication costs to improve heterogeneous edge and end models’ accuracy by at least 5.16% and 2.77% compared with five baselines. The proposed algorithm outperforms others by at least 9.78% in terms of global cost.
Förderung
- National Key R&D Program of China
- Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China
- National Natural Science Foundation of China
- New Generation Information Technology Innovation
- Fundamental Research Funds for the Central Universities
- Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing University
- Jiangsu High-Level Innovation and Entrepreneurship (Shuangchuang) Program
- Hong Kong Scholars Program
Zitieren
APA
Yu, E., Dai, H., Zhang, H., Qu, Y., Wu, T., Cheng, P., Hou, S., Zheng, Z., Wu, F., & Chen, G. (2026). Edge-End Heterogeneous Collaborative Learning by Prototype Selection and Edge Association. IEEE Transactions on Parallel and Distributed Systems, 37(7), 1485-1502. https://doi.org/10.1109/tpds.2026.3678282
Vancouver
Yu E, Dai H, Zhang H, Qu Y, Wu T, Cheng P, et al. Edge-End Heterogeneous Collaborative Learning by Prototype Selection and Edge Association. IEEE Transactions on Parallel and Distributed Systems. 2026;37(7):1485-1502. doi:10.1109/tpds.2026.3678282
BibTeX
@article{Yu2026,
author = {Yu, Enze and Dai, Haipeng and Zhang, Haihan and Qu, Yuben and Wu, Tao and Cheng, Penghuan and Hou, Sujin and Zheng, Zhenzhe and Wu, Fan and Chen, Guihai},
title = {Edge-End Heterogeneous Collaborative Learning by Prototype Selection and Edge Association},
journal = {IEEE Transactions on Parallel and Distributed Systems},
year = {2026},
volume = {37},
number = {7},
pages = {1485--1502},
doi = {10.1109/tpds.2026.3678282}
}
EUVIMED