Performance Evaluation of Federated Learning Over Wireless Mesh Networks with Low-Capacity Devices

Abstract

Federated learning is a distributed learning technique in which a machine learning model is trained collaboratively among several nodes. While the privacy preservation of the training data is one of the important promises of federated learning, there is also an opportunity to use low capacity devices for machine learning model training by taking advantage of the fact that the training effort is divided among many nodes. In this paper we conduct experiments with a federated learning network deployed on several low capacity devices connected to a wireless mesh network. The measurements show the hardware capacity and link bandwidth of the clients on the federated learning process. The results suggest that for heterogeneous networks the federated learning clients should be extended with more autonomous decision capacities according to the network and local conditions.

Integrating a Neural Network Library in Embedded Federated Learning

“…If the diversity of patterns in the training data is not sufficiently provided, doing model training by federated learning could be explored for improving an autoencoder's classification accuracy into normal and anomaly data. There could also be the potential to leverage a server's capacity to adapt the training to be done at each client [12].…”