FedAC: An Adaptive Clustered Federated Learning Framework for Heterogeneous Data
This addresses the problem of data heterogeneity in federated learning for distributed systems, offering an incremental improvement over existing clustered methods.
The paper tackles performance deterioration in federated learning due to data heterogeneity by proposing FedAC, an adaptive clustered framework that integrates global and intra-cluster knowledge, uses an online model similarity metric, and fine-tunes cluster numbers, achieving test accuracy improvements of around 1.82% on CIFAR-10 and 12.67% on CIFAR-100 compared to state-of-the-art methods.
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.