Abstract: In federated learning (FL),the distribution of data in clients is always heterogeneous,which makes the unified model trained in FL unable to meet the demand of each client. To combat this issue, a personalized federated learning algorithm with meta learning and knowledge distillation is proposed,in which the knowledge distillation and meta-learning with FL and incorporating the personalization are combined into the training of FL. In each global iteration,the global model(teacher model) update itself according to the feedback from the local model ( student model) during the knowledge distillation. Therefore,each client can obtain a better personalized model. Simulation results show that compared with the existing personalized algorithms, the proposed algorithm can achieve a better compromise between global accuracy and personalization accuracy while improving the personalization accuracy.

Key words: federated learning , meta-learning , knowledge distillation , personalization