Data scarcity and heterogeneity pose significant performance challenges for personalized federated learning, and these challenges are mainly reflected in overfitting and low precision in existing methods. To overcome these challenges, a multi-layer multi-fusion strategy framework is proposed in this paper, i.e., the server adopts the network layer parameters of each client upload model as the basic unit of fusion for information-sharing calculation. Then, a new fusion strategy combining personalized and generic is purposefully proposed, and the network layer number fusion threshold of each fusion strategy is designed according to the network layer function. Under this mechanism, the L2-Norm negative exponential similarity metric is employed to calculate the fusion weights of the corresponding feature extraction layer parameters for each client, thus improving the efficiency of heterogeneous data personalized collaboration. Meanwhile, the federated global optimal model approximation fusion strategy is adopted in the network full-connect layer, and this generic fusion strategy alleviates the overfitting introduced by forceful personalized. Finally, the experimental results show that the proposed method is superior to the state-of-the-art methods.

翻译：数据稀缺性和异质性对个性化联邦学习带来了显著的性能挑战，这些挑战主要体现在现有方法的过拟合和低精度问题上。为克服这些挑战，本文提出了一种多层多融合策略框架，即服务器采用各客户端上传模型的网络层参数作为融合的基本单元进行信息共享计算。然后，针对性地提出了一种结合个性化与通用性的新型融合策略，并根据网络层功能设计了每种融合策略的网络层数融合阈值。在此机制下，采用L2-Norm负指数相似度度量计算各客户端对应特征提取层参数的融合权重，从而提升异质性数据个性化协作的效率。同时，在网络全连接层采用联邦全局最优模型近似融合策略，这种通用融合策略缓解了强行个性化带来的过拟合问题。最后，实验结果表明，所提方法优于当前最先进的方法。