DAG Blockchain-based Personalized Federated Mutual learning in Internet of Vehicles

 Federated learning (FL) emerges as a distributed training method in the Internet of Vehicles (IoVs), allowing connected and automated vehicles (CAVs) to train a global model by exchanging models instead of raw data, protecting data privacy. Due to the limitation of model accuracy and communication overhead in FL, in this paper, we propose a directed acyclic graph (DAG) blockchain-based IoV that comprises a DAG layer and a CAV layer for model sharing and training, respectively. Furthermore, a DAG blockchain-based asynchronous federated mutual learning (DAFML) algorithm is introduced to improve the model performance, which utilizes a student-teacher model in the local training and a mutual distillation method that enables models to be partially updated using mutual transferred knowledge. Moreover, to further improve the model accuracy, the personalized weight is designed to adjust the mutual distillation in the model updating. Simulation results demonstrate that the proposed DAFML algorithm outperforms other benchmarks in terms of the model accuracy and distillation ratio.