SplitFed: When Federated Learning Meets Split Learning

Federated learning (FL) and split learning (SL) are two recent distributed machine learning (ML) approaches that have gained attention due to their inherent privacy-preserving capabilities. Both approaches follow a model-to-data scenario, in that an ML model is sent to clients for network training and testing. However, FL and SL show contrasting strengths and weaknesses. For example, while FL performs faster than SL due to its parallel client-side model generation strategy, SL provides better privacy than FL due to the ML model architecture split between clients and the server. In contrast to FL, SL enables ML training with clients having low computing resources as the client trains only the first few layers of the split ML network model. In this paper, we present a novel approach, named splitfed (SFL), that amalgamates the two approaches eliminating their inherent drawbacks. SFL splits the network architecture between the clients and server as in SL to provide a higher level of privacy than FL. Moreover, it offers better efficiency than SL by incorporating the parallel ML model update paradigm of FL. Our empirical results, on uniformly distributed horizontally partitioned HAM10000 and MNIST datasets with multiple clients, show that SFL provides similar communication efficiency and test accuracy as SL, while significantly decreasing - by four to six times - its computation time per global epoch than in SL for both datasets. Furthermore, as in SL, its communication efficiency over FL improves with the number of clients. To further enhance privacy, we integrate a differentially private local model training mechanism to SFL and test its performance on AlexNet with the MNIST dataset under various privacy levels.