Autoencoder-Enhanced Federated Learning with Reduced Overhead and Lower Latency

This paper investigates the application of autoencoder (AE) in supporting the training process of federated learning by reducing communication overhead and latency. We propose a scheduling algorithm to determine when and how to use autoencoder during training. Our simulation shows that federated learning with an au-toencoder significantly reduces communication overhead without compromising testing accuracy. Moreover, the testing accuracy curve shows a more consistent increase over training rounds in federated learning with an autoen-coder than in federated learning without an autoencoder. Additionally, the latency of federated learning with an autoencoder is lower than that of federated learning without an autoencoder.