Feature Map Compression for Split Learning in Mobile Wireless Environment: Theory and Practice
- 25 May 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. PP (15361233) , 1-16
Abstract
Split Learning (SL) enables collaborative model training by distributing computation between resource constrained mobile edge devices and a central server. In this distributed framework, mobile edge devices compute the early layers of the model and transmit feature maps to the server. However, due to practical mobile wireless bandwidth limitations, these feature maps should be compressed before transmission. In this paper, we propose a lightweight Mask-Encoded Spar sification (MS) compressor that enhances Top-k sparsification with a narrow-bit mask, significantly reducing compression error while improving computational and communication efficiency. Our theoretical analyses reveal that feature map compression generally induces estimator bias in the gradients. Furthermore, we establish the relationships between compression error and convergence, as well as between the choice of cutlayer and output error. The first relationship demonstrates that reducing compression error facilitates convergence, confirming the advantage of MS, whereas the second provides theoretical guidance for determining the cutlayer, indicating that earlier layers are more sensitive to compression errors. Extensive experiments on vision and language models demonstrate that our method outperforms existing compression techniques in terms of compression error and model performance, achieving up to a 21.38× speedup in communication efficiency under wireless environments.Keywords
Funding Information
- National Natural Science Foundation of China (62441225)
- Basic research program of Jiangsu (BK20253011)
- Hong Kong Scholars Program (XJ2024010)
- Research Grants Council of the Hong Kong Special Administrative Region (CityU11212524)
- Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China (JYB2025XDXM118)
- Overseas Expertise Introduction Center for Discipline Innovation of Food Nutrition and Human Health (B26023)
This publication has 34 references indexed in Scilit:
- Task-Oriented Communications for Visual Navigation with Edge-Aerial Collaboration in Low Altitude Economy2025
- FLM-TopK: Expediting Federated Large Language Model Tuning by Sparsifying Intervalized Gradients2025
- A Comprehensive Survey on Communication-Efficient Federated Learning in Mobile Edge EnvironmentsIEEE Communications Surveys & Tutorials, 2025
- JointSQ: Joint Sparsification-Quantization for Distributed Learning2024
- Communication-efficient Federated Learning with Single-Step Synthetic Features Compressor for Faster Convergence2023
- Scientific discovery in the age of artificial intelligenceNature, 2023
- Communication-Efficient Federated Learning for Heterogeneous Edge Devices Based on Adaptive Gradient Quantization2023
- The incremental online k-means clustering algorithm and its application to color quantizationExpert Systems with Applications, 2022
- Qsparse-Local-SGD: Distributed SGD With Quantization, Sparsification, and Local ComputationsIEEE Journal on Selected Areas in Information Theory, 2020
- Deep Residual Learning for Image Recognition2016