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

2026-03-10

AI Summary

This work addresses the high communication overhead in Split Learning caused by transmitting intermediate features (smashed data) by proposing an Adaptive Channel Pruning scheme for Split Learning (ACP-SL). The method introduces a Label-aware Channel Importance Scoring (LCIS) module to dynamically evaluate the contribution of each channel to the target task and integrates an Adaptive Channel Pruning (ACP) mechanism that removes redundant channels on the client side in real time, substantially compressing uplink data transmission. Experimental results demonstrate that ACP-SL not only reduces communication costs but also maintains or even improves model accuracy while achieving target performance in fewer training rounds, effectively balancing efficiency and precision.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Learning to Search
• Computer Vision: Learning & Optimization for CV

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Security and privacy of machine learning and AI applications
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• Split Learning
• Communication Overhead
• Channel Pruning
• Smashed Data
• Label-Aware

Innovation

• Split Learning
• Channel Pruning
• Label-Aware Scoring
• Communication Efficiency
• Adaptive Compression