Different from conventional federated learning, personalized federated learning (PFL) is able to train a customized model for each individual client according to its unique requirement. The mainstream approach is to adopt a kind of weighted aggregation method to generate personalized models, in which weights are determined by the loss value or model parameters among different clients. However, such kinds of methods require clients to download others' models. It not only sheer increases communication traffic but also potentially infringes data privacy. In this paper, we propose a new PFL algorithm called \emph{FedDWA (Federated Learning with Dynamic Weight Adjustment)} to address the above problem, which leverages the parameter server (PS) to compute personalized aggregation weights based on collected models from clients. In this way, FedDWA can capture similarities between clients with much less communication overhead. More specifically, we formulate the PFL problem as an optimization problem by minimizing the distance between personalized models and guidance models, so as to customize aggregation weights for each client. Guidance models are obtained by the local one-step ahead adaptation on individual clients. Finally, we conduct extensive experiments using five real datasets and the results demonstrate that FedDWA can significantly reduce the communication traffic and achieve much higher model accuracy than the state-of-the-art approaches.

翻译：与传统联邦学习不同，个性化联邦学习（PFL）能够根据每个客户端的独特需求为其训练定制化模型。主流方法采用一种加权聚合方式来生成个性化模型，其中权重由不同客户端间的损失值或模型参数决定。然而，此类方法要求客户端下载其他客户端的模型，不仅大幅增加通信流量，还可能侵犯数据隐私。本文提出一种名为FedDWA（基于动态权重调整的联邦学习）的新型PFL算法来解决上述问题，该方法利用参数服务器（PS）基于从客户端收集的模型计算个性化聚合权重。通过这种方式，FedDWA能以更低的通信开销捕捉客户端间的相似性。具体而言，我们将PFL问题形式化为一个优化问题，通过最小化个性化模型与引导模型之间的距离来为每个客户端定制聚合权重。引导模型是通过对单个客户端进行局部单步前向自适应获得的。最后，我们使用五个真实数据集进行了广泛实验，结果表明FedDWA能显著降低通信流量，并实现比现有最先进方法更高的模型精度。