Dispersed Federated Learning: Vision, Taxonomy, and Future Directions

The ongoing deployments of the Internet of Things (IoT)-based smart applications are spurring the adoption of machine learning as a key technology enabler. To overcome the privacy and overhead challenges of centralized machine learning, there has been significant recent interest in the concept of federated learning. Federated learning offers on-device machine learning without the need to transfer end-device data to a third party location. However, federated learning has robustness concerns because it might stop working due to a failure of the aggregation server (e.g., due to a malicious attack or physical defect). Furthermore, federated learning over IoT networks requires a significant amount of communication resources for training. To cope with these issues, we propose a novel framework of dispersed federated learning (DFL) that is based on true decentralization. We opine that DFL will serve as a practical implementation of federated learning for various IoT-based smart applications such as smart industries and intelligent transportation systems. First, the fundamentals of the DFL are presented. Second, a taxonomy is devised with a qualitative analysis of various DFL schemes. Third, a DFL framework for IoT networks is proposed with a matching theory-based solution. Finally, an outlook on future research directions is presented.

Automated summary

The concept of federated learning is gaining significant interest as a decentralized training method for IoT applications, offering advantages in privacy and communication resources. The dispersed federated learning framework provides a practical implementation for various IoT smart applications.