Federated learning is an emerging distributed machine learning framework in the Internet of Vehicles (IoV). In IoV, millions of vehicles are willing to train the model to share their knowledge. Maintaining an active state means the participants must update their state to the FL server in a fixed interval and participate in the next round. However, the cost of maintaining an active state is very large when there are a huge number of participating vehicles. In this paper, we propose a distributed client selection scheme to reduce the cost of maintaining the active state for all participants. The clients with the highest evaluation are elected among the neighbors. In the evaluator, four variables are considered, including the sample quantity, available throughput, computational capability, and the quality of the local dataset. We adopt fuzzy logic as the evaluator since the closed-form solution over four variables does not exist. Extensive simulation results show that our proposal approximates the centralized client selection in terms of accuracy and can significantly reduce the communication overhead.
Non-IID is one of the key challenges in federated learning. Data heterogeneity may lead to slower convergence, reduced accuracy, and more training rounds. To address the common Non-IID data distribution problem in federated learning, we propose a comprehensive dynamic optimization approach based on existing methods. It leverages MAP estimation of the Dirichlet parameter to dynamically adjust the regularization coefficient and introduces orthogonal gradient coefficients to mitigate gradient interference among different classes. The approach is compatible with existing federated learning frameworks and can be easily integrated. Achieves significant accuracy improvements in both mildly and severely Non-IID scenarios while maintaining a strong performance lower bound.