Research

Paper

TESTING March 10, 2026

Exploiting Label-Aware Channel Scoring for Adaptive Channel Pruning in Split Learning

Authors

Jialei Tan, Zheng Lin, Xiangming Cai, Ruoxi Zhu, Zihan Fang, Pingping Chen, Wei Ni

Abstract

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. To address this challenge, we propose an 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 consistently outperforms benchmark schemes in test accuracy. Furthermore, it reaches a target test accuracy in fewer training rounds, thereby reducing communication overhead.

Metadata

arXiv ID: 2603.09792
Provider: ARXIV
Primary Category: cs.LG
Published: 2026-03-10
Fetched: 2026-03-11 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.09792v1</id>\n    <title>Exploiting Label-Aware Channel Scoring for Adaptive Channel Pruning in Split Learning</title>\n    <updated>2026-03-10T15:25:08Z</updated>\n    <link href='https://arxiv.org/abs/2603.09792v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.09792v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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. To address this challenge, we propose an 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 consistently outperforms benchmark schemes in test accuracy. Furthermore, it reaches a target test accuracy in fewer training rounds, thereby reducing communication overhead.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-10T15:25:08Z</published>\n    <arxiv:comment>6 pages, 6 figures,</arxiv:comment>\n    <arxiv:primary_category term='cs.LG'/>\n    <author>\n      <name>Jialei Tan</name>\n    </author>\n    <author>\n      <name>Zheng Lin</name>\n    </author>\n    <author>\n      <name>Xiangming Cai</name>\n    </author>\n    <author>\n      <name>Ruoxi Zhu</name>\n    </author>\n    <author>\n      <name>Zihan Fang</name>\n    </author>\n    <author>\n      <name>Pingping Chen</name>\n    </author>\n    <author>\n      <name>Wei Ni</name>\n    </author>\n  </entry>"
}