SL-ACC: A communication-efficient split learning framework with adaptive channel-wise compression
Author Identifier (ORCID)
Abstract
The increasing complexity of neural networks poses a significant barrier to the deployment of distributed machine learning (ML) on resource-constrained devices, such as federated learning (FL). Split learning (SL) offers a promising solution by offloading the primary computing load from edge devices to a server via model partitioning. However, as the number of participating devices increases, the transmission of excessive smashed data (i.e., activations and gradients) becomes a major bottleneck for SL, slowing down the model training. To tackle this challenge, we propose a communication-efficient SL framework, named SL-ACC, which comprises two key components: adaptive channel importance identification (ACII) and channel grouping compression (CGC). ACII first identifies the contribution of each channel in the smashed data to model training using Shannon entropy. Following this, CGC groups the channels based on their entropy and performs group-wise adaptive compression to shrink the transmission volume without compromising training accuracy. Extensive experiments across various datasets validate that our proposed SL-ACC framework takes considerably less time to achieve a target accuracy than state-of-the-art benchmarks.
Keywords
distributed learning, edge intelligence, split learning
Document Type
Journal Article
Date of Publication
8-1-2026
E-ISSN
19399359
ISSN
00189545
Volume
75
Issue
8
Publication Title
IEEE Transactions on Vehicular Technology
Publisher
IEEE
School
School of Engineering
Funding Information
Xiamen Science and Technology Program: Open Call for Proposals Project (Grant Number: 3502Z20251017), Industry-University Cooperation Project of Fujian Universities (Grant Number: 2024H6020), Natural Science Foundation of Xiamen Municipality (Grant Number: 3502Z202572029), Research Project of the National High-Tech Ship Special Program (Grant Number: CBG4N21-4-4).
Copyright
subscription content
First Page
18826
Last Page
18831
Recommended Citation
Lin, Z., Lin, Z., Yang, M., Huang, J., Zhang, Y., Fang, Z., Du, X., Chen, Z., Zhu, S., & Ni, W. (2026). SL-ACC: A communication-efficient split learning framework with adaptive channel-wise compression. IEEE Transactions on Vehicular Technology, 75(8), 18826–18831. https://doi.org/10.1109/TVT.2026.3679518