Due to the rapid development of wireless communication and edge intelligence, the industrial Internet of Things (IIoT) has found many applications in the engineering sector, such as smart cities, intelligent transportation, or smart video monitoring. To support the development of IIoT-based engineering, many promising techniques have been proposed, among which federated learning and optimization are among the most promising. Federated learning can ensure information security during the exchange of big data, protect the privacy of terminal and personal data, ensure legal compliance, and carry out efficient machine learning between multiple participants or multiple computing nodes. Due to these advantages, federated leaning has been widely and successfully applied in many engineering areas, such as wireless sensor networks, privacy protection, big data analysis, financial data exchange, and civil engineering.

However, federated learning and optimization also face several critical challenges in IIoT-based engineering, from implementation to data exchange overheads. One challenge is the distribution characteristics of the data in IIoT-based engineering, where in practice data may not follow an independent and identical distribution. Another challenge is the lack of interaction among nodes, which may cause the whole system to lose robustness and result in high exploration costs. The applications of federated leaning into advanced communication and computing techniques, such as unmanned aerial vehicles (UAV), caching, and massive multiple input multiple output (MIMO) techniques, is also challenging, as a joint optimization framework must be built.

The objective of this Special Issue is to collect emerging theories, algorithms, and applications to solve the challenges related to federated learning and its application in IIoT- based engineering. We hope to give a new view of federated learning and optimization through its applications in IIoT-based engineering.

Potential topics include but are not limited to the following:

• Federated learning for IIoT-based engineering
• Deep learning and optimization for industrial IIoT-based engineering
• Fundamental analysis of federated learning
• Convergence analysis of deep learning
• Intelligent source recognition
• Advanced privacy protection techniques for federated learning
• Federated learning with UAVs
• Federated optimization with caching
• Federated leaning with massive MIMO
• Wireless sensor networks in IIoT engineering
• Engineering applications of IIoT with federated learning
• Deep learning and reinforcement learning