Next Generation Federated Learning for Edge Devices: An Overview

Federated learning (FL) is a popular distributed machine learning paradigm involving numerous edge devices with enhanced privacy protection. Recently, an extensive literature has been developing on the research which aims at promoting the innovations of FL. Motivated by the explosive growth in FL research, this paper studies the next generation of Federated Learning for edge devices. We identify two key challenges, system efficiency and data heterogeneity, which impede the development of FL. We introduce some representative works which contribute to these challenges. Besides, we anticipate the future directions of FL for edge devices and provide guidance for future FL research.