Clustered federated learning (CFL) is proposed to mitigate the performance deterioration stemming from data heterogeneity in federated learning (FL) by grouping similar clients for cluster-wise model training. However, current CFL methods struggle due to inadequate integration of global and intra-cluster knowledge and the absence of an efficient online model similarity metric, while treating the cluster count as a fixed hyperparameter limits flexibility and robustness. In this paper, we propose an adaptive CFL framework, named FedAC, which (1) efficiently integrates global knowledge into intra-cluster learning by decoupling neural networks and utilizing distinct aggregation methods for each submodule, significantly enhancing performance; (2) includes a costeffective online model similarity metric based on dimensionality reduction; (3) incorporates a cluster number fine-tuning module for improved adaptability and scalability in complex, heterogeneous environments. Extensive experiments show that FedAC achieves superior empirical performance, increasing the test accuracy by around 1.82% and 12.67% on CIFAR-10 and CIFAR-100 datasets, respectively, under different non-IID settings compared to SOTA methods.

翻译：聚类联邦学习（CFL）通过将相似客户端分组进行簇级模型训练，旨在缓解联邦学习（FL）中由数据异构性导致的性能退化问题。然而，当前CFL方法因未能充分整合全局与簇内知识、缺乏高效的在线模型相似性度量，且将簇数量视为固定超参数而限制了灵活性与鲁棒性。本文提出一种名为FedAC的自适应CFL框架，该框架：（1）通过解耦神经网络并针对各子模块采用不同聚合方法，将全局知识高效整合至簇内学习，显著提升性能；（2）引入基于降维的高性价比在线模型相似性度量方法；（3）包含簇数量微调模块，增强其在复杂异构环境中的适应性与可扩展性。大量实验表明，FedAC实现了优越的实证性能：在CIFAR-10和CIFAR-100数据集上，不同非独立同分布设置下，相较于现有最优方法，测试准确率分别提升约1.82%和12.67%。