Federated Learning (FL) aims to learn a single global model that enables the central server to help the model training in local clients without accessing their local data. The key challenge of FL is the heterogeneity of local data in different clients, such as heterogeneous label distribution and feature shift, which could lead to significant performance degradation of the learned models. Although many studies have been proposed to address the heterogeneous label distribution problem, few studies attempt to explore the feature shift issue. To address this issue, we propose a simple yet effective algorithm, namely \textbf{p}ersonalized \textbf{Fed}erated learning with \textbf{L}ocal \textbf{A}ttention (pFedLA), by incorporating the attention mechanism into personalized models of clients while keeping the attention blocks client-specific. Specifically, two modules are proposed in pFedLA, i.e., the personalized single attention module and the personalized hybrid attention module. In addition, the proposed pFedLA method is quite flexible and general as it can be incorporated into any FL method to improve their performance without introducing additional communication costs. Extensive experiments demonstrate that the proposed pFedLA method can boost the performance of state-of-the-art FL methods on different tasks such as image classification and object detection tasks.

翻译：联邦学习（FL）旨在学习一个单一的全局模型，使中央服务器能够在不访问客户端本地数据的情况下帮助其训练模型。FL面临的关键挑战在于不同客户端的本地数据异质性，例如异质标签分布与特征偏移，这可能导致所学模型性能显著下降。尽管已有大量研究致力于解决异质标签分布问题，但鲜有工作尝试探索特征偏移问题。为应对这一挑战，我们提出一种简单而有效的算法，即基于局部注意力的个性化联邦学习（pFedLA），通过将注意力机制融入客户端的个性化模型中，同时保持注意力模块的客户端特异性。具体而言，pFedLA包含两个模块：个性化单注意力模块与个性化混合注意力模块。此外，所提出的pFedLA方法具有高度的灵活性与通用性，可集成至任意联邦学习框架中，在不引入额外通信成本的前提下提升其性能。大量实验表明，所提出的pFedLA方法能在图像分类、目标检测等不同任务上提升当前最优联邦学习方法的性能。