FedDiverse: Tackling Data Heterogeneity in Federated Learning with Diversity-Driven Client Selection
This addresses the problem of slow convergence and reduced model generalization in federated learning for applications with non-identically distributed data, though it is incremental as it builds on existing FL methods.
The paper tackled data heterogeneity in federated learning by proposing FedDiverse, a client selection algorithm that promotes collaboration between clients with complementary data distributions, resulting in enhanced performance and robustness across seven new datasets with low overhead.
Federated Learning (FL) enables decentralized training of machine learning models on distributed data while preserving privacy. However, in real-world FL settings, client data is often non-identically distributed and imbalanced, resulting in statistical data heterogeneity which impacts the generalization capabilities of the server's model across clients, slows convergence and reduces performance. In this paper, we address this challenge by proposing first a characterization of statistical data heterogeneity by means of 6 metrics of global and client attribute imbalance, class imbalance, and spurious correlations. Next, we create and share 7 computer vision datasets for binary and multiclass image classification tasks in Federated Learning that cover a broad range of statistical data heterogeneity and hence simulate real-world situations. Finally, we propose FEDDIVERSE, a novel client selection algorithm in FL which is designed to manage and leverage data heterogeneity across clients by promoting collaboration between clients with complementary data distributions. Experiments on the seven proposed FL datasets demonstrate FEDDIVERSE's effectiveness in enhancing the performance and robustness of a variety of FL methods while having low communication and computational overhead.