This paper proposes LCFL, a novel clustering metric for evaluating clients' data distributions in federated learning. LCFL aligns with federated learning requirements, accurately assessing client-to-client variations in data distribution. It offers advantages over existing clustered federated learning methods, addressing privacy concerns, improving applicability to non-convex models, and providing more accurate classification results. LCFL does not require prior knowledge of clients' data distributions. We provide a rigorous mathematical analysis, demonstrating the correctness and feasibility of our framework. Numerical experiments with neural network instances highlight the superior performance of LCFL over baselines on several clustered federated learning benchmarks.

翻译：本文提出LCFL，一种用于评估联邦学习中客户端数据分布的新型聚类度量方法。LCFL符合联邦学习要求，能够准确评估客户端间数据分布的差异。相较于现有聚类联邦学习方法，该方法具有多重优势：解决了隐私顾虑、提升了对非凸模型的适用性，并能提供更精确的分类结果。LCFL无需客户端数据分布的先验知识。我们提供了严格的数学分析，证明了该框架的正确性与可行性。基于神经网络实例的数值实验表明，在多个聚类联邦学习基准测试中，LCFL均优于基线方法。