Due to the rapid development in wireless communication and edge computing, unmanned aerial vehicle (UAV) networks have been widely applied in many scenarios, such as emergency search and rescue, climate monitoring, traffic control, forest fire detection, freight logistics, and aerial photography. The key characteristics of UAV communication are its high mobility and flexibility; however, this is then the cause of much difficulty in terms of UAV control, scheduling, and networking. To support the development of UAV communication networks, federated learning has been proposed to train a global model by exchanging model parameters or intermediate results without exchanging local private data. In addition, as a high-level machine learning method, meta-learning has been also proposed by researchers to study many tasks together, which involves a hierarchical system that learns to learn a new challenge with distributed hierarchically organized metadata. The high potential of meta federated learning has led to much research into its application in UAV communication networks.

However, there are still several critical challenges in the application of meta federated learning in UAV communication networks. One critical challenge is the convergence rate of meta federated learning, which affects the control and networking of UAV communications, especially in latency-sensitive application scenarios. One more challenge is explaining the inherent mechanisms in meta federated learning, as some explainable methods must be developed for UAV communication. Another critical challenge is how to incorporate meta federated learning with communication and computing techniques, where the communication and computing overhead should be substantially reduced to guarantee network performance and feasibility.

The aim of this Special Issue is to collate both original research and review articles investigating the significance of meta federated learning for UAV communication networks. With this Special Issue, we hope to discover the potential of UAV communication networks by using meta federated learning in Internet of Things (IoT)-enabled edge computing. Submissions discussing informative and effective techniques that can support intelligent UAV communication networks are highly encouraged.

Potential topics include but are not limited to the following:

• Meta federated learning
• UAV communication
• Performance analysis of meta learning
• Resource management for UAV communication
• Edge computing with meta learning
• Federated learning cache
• Explainable meta federated learning
• Meta precoding design of UAV communication
• Federated detection algorithms for UAV communication
• Energy-efficient federated UAV communication
• Industrial IoT networks
• Applications of meta-learning