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

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 (S^2FL), 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, S^2FL 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, S^2FL can alleviate the performance degradation caused by data heterogeneity. Experimental results demonstrate that, compared to conventional SFL, S^2FL can achieve up to 16.5\% inference accuracy improvement and 3.54X training acceleration.

Tasks

Reproductions