SplitFed: When Federated Learning Meets Split Learning

TL;DR

This paper introduces SplitFed learning (SFL), a hybrid of federated and split learning that enhances privacy, reduces computation time, and improves communication efficiency in distributed machine learning.

Contribution

The paper proposes SFL, combining FL and SL to overcome their limitations, and incorporates differential privacy and PixelDP for enhanced data privacy and robustness.

Findings

SFL achieves similar accuracy and communication efficiency as SL.

SFL significantly reduces computation time compared to SL.

Communication efficiency of SFL improves with more clients.

Abstract

Federated learning (FL) and split learning (SL) are two popular distributed machine learning approaches. Both follow a model-to-data scenario; clients train and test machine learning models without sharing raw data. SL provides better model privacy than FL due to the machine learning model architecture split between clients and the server. Moreover, the split model makes SL a better option for resource-constrained environments. However, SL performs slower than FL due to the relay-based training across multiple clients. In this regard, this paper presents a novel approach, named splitfed learning (SFL), that amalgamates the two approaches eliminating their inherent drawbacks, along with a refined architectural configuration incorporating differential privacy and PixelDP to enhance data privacy and model robustness. Our analysis and empirical results demonstrate that (pure) SFL provides similar test accuracy and communication efficiency as SL while significantly decreasing its computation time per global epoch than in SL for multiple clients. Furthermore, as in SL, its communication efficiency over FL improves with the number of clients. Besides, the performance of SFL with privacy and robustness measures is further evaluated under extended experimental settings.