Exploiting Adaptive Channel Pruning for Communication-Efficient Split Learning

TL;DR

This paper introduces an adaptive channel pruning method for split learning that reduces communication costs by selectively compressing feature representations, while maintaining high accuracy and faster convergence.

Contribution

It proposes a novel label-aware channel importance scoring and adaptive pruning scheme to optimize communication efficiency in split learning.

Findings

Outperforms benchmark schemes in test accuracy.

Reaches target accuracy with fewer training rounds.

Reduces communication overhead significantly.

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.