Pseudo-Label Selection-Based Federated Semi-Supervised Learning Framework for Vehicular Networks

Abstract

In vehicular networks, federated learning (FL) has been used for secure and distributed edge intelligence to support deep neural network (DNN) model training. In the FL, the roadside units (RSUs) and vehicles act as the parameter servers and clients, respectively. However, the raw data collected by the vehicles are normally unlabeled, which can hardly meet the requirements of the supervised learning tasks. To resolve the related issues, a federated semi-supervised learning (FSSL) framework is proposed in this paper. By leveraging semi-supervised learning (SSL), the framework can implement the model training with unlabeled data in vehicles and a small set of manually annotated data in the RSU. Furthermore, a pseudo-label selection method is developed for the vehicles to improve the local pseudo-label prediction accuracy and the convergence of global model training. Simulation experiments have been conducted to evaluate the performance of the proposed FSSL framework. The experimental results show that the proposed framework can effectively utilize unlabeled data in vehicular networks and complete the task of DNN model training.