Exploiting Label-Aware Channel Scoring for Adaptive Channel Pruning in Split Learning
IEEE Communications Letters · 2026 · 30 · 2800-2804
DOI: 10.1109/lcomm.2026.3717104 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Communications Letters, 2026. Verfasst von Jialei Tan und 6 weiteren Autor:innen. Die Arbeit nennt 10 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Science Foundation of Fujian Province.
Abstract (Originalsprache)
Split learning (SL) transfers most of the training workload to the server, which alleviates computational burden on client devices. However, the transmission of intermediate feature representations, referred to as smashed data, incurs significant communication overhead, particularly when a large number of client devices are involved. Existing SL methods apply uniform compression across all channels, over-compressing smashed data associated with important channels while under-compressing smashed data corresponding to less important channels. To address this challenge, we propose a communication-efficient adaptive channel pruning-aided SL (ACP-SL) scheme. In ACP-SL, a label-aware channel importance scoring (LCIS) module is designed to generate channel importance scores, distinguishing important channels from less important ones. Based on these scores, an adaptive channel pruning (ACP) module is developed to prune less important channels, thereby compressing the corresponding smashed data and reducing the communication overhead. Experimental results show that ACP-SL outperforms most benchmark schemes in test accuracy. Furthermore, it reaches a target test accuracy in fewer training rounds, reducing communication overhead.
Förderung
- National Natural Science Foundation of China
- National Science Foundation of Fujian Province
Zitieren
APA
Tan, J., Cai, X., Lin, Z., Zhu, R., Fang, Z., Chen, P., & Ni, W. (2026). Exploiting Label-Aware Channel Scoring for Adaptive Channel Pruning in Split Learning. IEEE Communications Letters, 30, 2800-2804. https://doi.org/10.1109/lcomm.2026.3717104
Vancouver
Tan J, Cai X, Lin Z, Zhu R, Fang Z, Chen P, et al. Exploiting Label-Aware Channel Scoring for Adaptive Channel Pruning in Split Learning. IEEE Communications Letters. 2026;30:2800-2804. doi:10.1109/lcomm.2026.3717104
BibTeX
@article{Tan2026,
author = {Tan, Jialei and Cai, Xiangming and Lin, Zheng and Zhu, Ruoxi and Fang, Zihan and Chen, Pingping and Ni, Wei},
title = {Exploiting Label-Aware Channel Scoring for Adaptive Channel Pruning in Split Learning},
journal = {IEEE Communications Letters},
year = {2026},
volume = {30},
pages = {2800--2804},
doi = {10.1109/lcomm.2026.3717104}
}
EUVIMED