Federated Learning Models for Real-Time IoT: A Survey

Abstract

Training and Inferencing phases of Machine Learning (ML) are compute-intensive often requiring cloud-hosted resources. However real-time needs of Internet of Things (IoT) applications and variable and long latencies between the edge and the cloud require new ways to exploit clusters of edge devices and decentralized federated approaches to ML training/in-ferencing. Federated Machine Learning (FedML) is however fraught with many challenges including the need to discover resources heterogeneity in resource types leading to non-uniform execution times among cluster members increased incidences of failures and network disconnectivity leading to consistency issues preserving privacy of data the type of distributed ML algorithm used to require its availability on the chosen resources and many others. To address this plethora of challenges this early stage research surveys seven FedML approaches to investigate the feasibility of a privacy-preserving edge-centric distributed ML solutions on edge devices. We also discuss the open issues FedML still faces. Finally we highlight the trends and prospects towards future on-device and Edge AI.