Have Your Cake and Eat It Too: Toward Efficient and Accurate Split Federated Learning

2023/11/22 by Dengke Yan, Yan, Dengke, Hu Ming +11 · 1 citation
Computer Science · Engineering · #Distributed #FOS: Computer and information sciences #Internet Traffic Analysis and Secure E-voting #Machine Learning (cs.LG) #Parallel #Privacy-Preserving Technologies in Data #Traffic Prediction and Management Techniques #and Cluster Computing (cs.DC)

paper · pdf · doi:10.48550/arxiv.2311.13163

openalex publication_date 2023/11/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Due to its advantages in resource constraint scenarios, Split Federated Learning (SFL) is promising in AIoT systems. However, due to data heterogeneity and stragglers, SFL suffers from the challenges of low inference accuracy and low efficiency. To address these issues, this paper presents a novel SFL approach, named Sliding Split Federated Learning (S²FL), which adopts an adaptive sliding model split strategy and a data balance-based training mechanism. By dynamically dispatching different model portions to AIoT devices according to their computing capability, S²FL can alleviate the low training efficiency caused by stragglers. By combining features uploaded by devices with different data distributions to generate multiple larger batches with a uniform distribution for back-propagation, S²FL can alleviate the performance degradation caused by data heterogeneity. Experimental results demonstrate that, compared to conventional SFL, S²FL can achieve up to 16.5% inference accuracy improvement and 3.54X training acceleration.

Cited by

• Towards Straggler-Resilient Split Federated Learning: An Unbalanced Update Approach

Related

• FSL-SAGE: Accelerating Federated Split Learning via Smashed Activation Gradient Estimation
• Hierarchical Split Federated Learning: Convergence Analysis and System Optimization
• Effectively Heterogeneous Federated Learning: A Pairing and Split Learning Based Approach
• SemiSFL: Split Federated Learning on Unlabeled and Non-IID Data
• Communication and Storage Efficient Federated Split Learning