Internet of Things (IoT) applications, such as intelligent transportation and remote health monitoring, have result in incredible advances in the quality of life. In the IoT era, massive devices and a large amount of data require the deployment of machine learning approaches in order to provide high-quality smart services. However, IoT devices should not share personal data due to the risk of data misuse and leakage. As a distributed machine learning approach with data privacy, Federated Learning (FL) has attracted great attention in IoT applications in recent years. As FL technologies evolve, several challenges have emerged including convergence rate analysis, devices selection, resource allocation etc. Various theories, optimization algorithms, and sophisticated schemes have been proposed to tackle these challenges. Furthermore, applications in IoT can benefit from FL and IoT systems can provide effective security. However, further research is required to enable FL for IoT.

This Special Issue aims to bring together leading researchers and developers from both industry and academia to present their research on FL for IoT and to promote the development of IoT. We welcome both original research and review papers.

Potential topics include but are not limited to the following:

• Architecture and protocol design in FL for IoT
• Applications and services in FL for IoT
• Convergence rate analysis for FL
• Advanced federated optimization algorithms for enabling FL in IoT
• Artificial intelligence empowered FL for IoT
• Blockchain empowered FL for IoT
• Communication, computation, and cache resource management in FL for IoT
• Intelligent resource allocation in FL for IoT
• Security and privacy issues in FL for IoT
• Implementation/testbed/deployment for FL
• Personalized FL for IoT