The integration of federated learning (FL) with the Internet of Things (IoT) represents an advanced technological trend, combining the extensive connectivity of IoT with the powerful processing capabilities of FL to drive innovation and optimization across multiple domains. Given the heterogeneity of IoT devices and the variability in data distribution, developing strategies to enhance FL performance without overly burdening resource-constrained devices is crucial. This article proposes an FL algorithm based on generative artificial intelligence (GAI) for IoT devices with extreme heterogeneity in data and resources. The algorithm utilizes pretrained GAI models to generate new data, aligning the data distributions of individual IoT devices closer to independent and identically distributed (i.i.d.), thereby effectively reducing the heterogeneity of local data. Additionally, the proposed algorithm incorporates data synthesis and resource scheduling strategies to mitigate the heterogeneity of local device resources. Finally, we formulate a joint optimization problem aimed at minimizing total energy consumption while maximizing FL performance. Experimental results demonstrate that, under significant resource and data distribution disparities, most existing solutions struggle to converge, whereas the proposed method converges and achieves superior performance. Compared to existing GAI-based approaches, our method significantly reduces latency and energy consumption.

Metaverse is envisioned to merge the actual world with a virtual world to bring users unprecedented immersive feelings. To ensure user experience, federated learning (FL) has been expected as a critical enabler to provide metaverse users with high-quality sensing, communicating, and rendering. However, considering the limitation of wireless communication resources and the stringent requirements of users, collaborating with massive metaverse users to realize FL still has tremendous challenges. Most pioneer works on improving the performance of FL assume that the system states are static, which is unsuitable in the metaverse. Because the FL in the metaverse is always a complicated long-term iteration process, where the fluctuations of channel status and available computing resources of users are inevitable, a changeless strategy may lead to poor results. Therefore, this paper proposes an efficient FL scheme relying on dynamic user selection, gradient quantization, and resource allocation. Specifically, we derive the convergence error bound to reveal the impact of user selection, wireless transmission error, and gradient quantization error of each iteration on FL’s convergence. Based on the theoretical analysis, we jointly and dynamically optimize the user selection, gradient quantization, and resource allocation to minimize the error bound with time and energy consumption budgets. Furthermore, to make the formulated sequential decision-making problem tractable, we transform it into a Markov decision process and design a soft actor-critic-based solution. Extensive experiments validate that our proposed scheme has superior performance compared to conventional schemes in dynamic-changing network environments.

Recently deep neural networks (DNNs) are widely used in various fields. These intelligence applications, such as target recognition, are often computation-intensive and latency-sensitive. Since a single UAV's computing resource is limited, it is difficult to complete the DNN inference task independently. Partitioning the deep neural work into numerals subtasks and distributing them to multiple UAVs for collaborative computing seems a better way to finish the task. However, UAV usually works in a harsh environment, such as battlefield, disaster area, etc., and the link interruption or node failure in the inference process caused by uncertain factors may lead to failure of inference task. Hence, the reliability of DNN inference is of high importance. In this paper, we propose a deep Q learning-based DNN partitioning strategy for minimizing the energy consumption of DNN collaborative inference among multi-UAVs within latency and reliability requirements. To validate the effectiveness of the proposed strategy, a series of experiments are conducted on four kinds of typical DNNs (i.e., AlexNet, VGG19, GoogleNet, and ResNet). The simulation results prove the proposed strategy can effectively reduce the DNN inference cost under constraints.