The integration of Artificial Intelligence (AI) and the Internet of Things (IoT), also known as the Artificial intelligence of Things (AIoT), has breathed new life into IoT operations and human-machine interactions. However, resource-constrained IoT devices usually cannot provide sufficient data storage and processing capability for data storage and processing to build modern AI models. AIoT technologies have been applied to diverse fields such as smart cities, smart homes, and smart communities. When deploying AIoT devices in communities, it is often necessary to collect users' daily behavior data. Since community household behavior data refers to personal privacy, it is not suitable for centralized processing and can only be independently processed and analyzed.

A promising solution is to integrate lightweight computing technology into AIoT which exploits the privacy-preserving and storage capacity of servers on Federated Learning (FL). Therefore, methods like FL, are needed to train AIoT datasets without sharing data and breaching restrictions on privacy and property. User data does not leave the local area to satisfy lightweight computing but is able to effectively combine the data from various communities for joint modeling to effectively protect privacy.

This Special Issue aims to gather recent advances and novel contributions from academic researchers and industry practitioners on the vibrant topic of federated learning to achieve better development of AIoT with respect to lightweight computing and privacy-preserving. In addition, this Special Issue welcomes relevant researchers to discuss the latest developments in the feasibility of new applications of AIoT in edge computing and human-machine interactions. We welcome original research and review articles.

Potential topics include but are not limited to the following:

• FL-enabled lightweight computing architectures, frameworks, platforms, and protocols for AIoT
• Machine Learning (ML) techniques in edge computing for AIoT
• Edge network architecture and optimization for AI applications at scale
• FL-enabled smart city architecture and modeling
• AI and deep learning approaches for IoT in smart cities
• Privacy-preserving and security techniques for FL for user data
• Machine Learning (ML) and cognitive computing for AIoT in smart homes
• Collaborative FL-enabled AIoT operation and maintenance in smart cities
• Novel network and communication protocols for FL-enabled AIoT
• Energy-efficient edge network operations via AI algorithms
• Self-learning and adaptive networking protocols and algorithms
• Novel applications, and case studies with lightweight computing for AIoT
• AI modeling and performance analysis in lightweight computing for AIoT