摘要： 个性化联邦学习算法在处理非独立同分布（Non-IID,Non-Independent and Identically Distributed）数据集和客户端模型个性化方面有着巨大优势。而基于超网络的个性化联邦学习利用客户端各自的超网络实现了客户端模型的个性化训练。然而，针对客户端超网络参数和客户端数据的共享对客户端个性化模型的准确率的影响相对不明确。因此，本文提出多层超网络个性化联邦学习（pFedMHN,Multi-Layer Hypernetwork Personalized Federated Learning）框架，通过利用局部和全局超网络完成客户端超网络模型加权聚合，进而优化客户端模型。在服务器端学习全局超网络和每个客户端的多层局部超网络，并加权聚合得到客户端超网络，在客户端利用超网络参数迭代更新客户端模型，超网络参数的共享实现了客户端更精确的个性化模型。实验结果表明，在通用公开数据集上，在准确率上pFedMHN优于四种基准算法，有效解决了在Non-IID数据集上个性化联邦学习中面临的数据异构性和模型准确性问题，通过利用超网络参数和客户端数据共享实现了客户端更精确的个性化模型。

Abstract: Personalized federated learning algorithms have great advantages in handling non-independent and identically distributed (Non-IID) datasets and client-side model personalization. Personalized federated learning based on hypernetwork utilizes the client's own hypernetwork to achieve personalized client model. However, the impact of sharing client-side hypernetwork parameters and client-side data on the accuracy of client-side personalized models is still unclear. The multi-layer hypernetwork personalized federated learning (pFedMHN) framework is proposed to optimize client models through the weighted aggregation of local and global hypernetworks. The server learns a global hypernetwork and each client's multi-layer local hypernetworks, then aggregates them. Clients use these aggregated hypernetwork parameters to iteratively update their models, resulting in more accurate personalized models. Experimental results show that on general public datasets, pFedMHN outperforms four benchmark algorithms in terms of accuracy, effectively solves the problems of data heterogeneity and model accuracy faced in personalized federated learning on Non-IID datasets, and achieves a more accurate personalized model for clients by utilizing hypernetwork parameters and client data sharing.