Statistical heterogeneity across clients in a Federated Learning (FL) system increases the algorithm convergence time and reduces the generalization performance, resulting in a large communication overhead in return for a poor model. To tackle the above problems without violating the privacy constraints that FL imposes, personalized FL methods have to couple statistically similar clients without directly accessing their data in order to guarantee a privacy-preserving transfer. In this work, we design user-centric aggregation rules at the parameter server (PS) that are based on readily available gradient information and are capable of producing personalized models for each FL client. The proposed aggregation rules are inspired by an upper bound of the weighted aggregate empirical risk minimizer. Secondly, we derive a communication-efficient variant based on user clustering which greatly enhances its applicability to communication-constrained systems. Our algorithm outperforms popular personalized FL baselines in terms of average accuracy, worst node performance, and training communication overhead.

翻译：联邦学习（FL）系统中客户端之间的统计异质性会延长算法收敛时间并降低泛化性能，导致为获取劣质模型而付出高昂通信开销。为在不违反FL隐私约束的前提下解决上述问题，个性化FL方法必须在不直接访问用户数据的情况下，将统计特征相似的客户端耦合，从而确保隐私保护的迁移。本文在参数服务器（PS）端设计了以用户为中心的聚合规则，该规则基于易于获取的梯度信息，并能为每个FL客户端生成个性化模型。所提出的聚合规则受加权聚合经验风险最小化器上界的启发。其次，我们推导出基于用户聚类的通信高效变体，极大增强了其在通信受限系统中的适用性。在平均精度、最差节点性能及训练通信开销方面，我们的算法均优于主流个性化FL基线方法。