Federated cINN Clustering for Accurate Clustered Federated Learning

TL;DR

This paper introduces FCCA, a clustering algorithm for federated learning that groups clients based on data similarity, improving model performance amid data heterogeneity.

Contribution

The paper proposes a novel FCCA method that uses a global encoder and generative modeling to cluster clients effectively in federated learning.

Findings

FCCA outperforms existing clustered FL algorithms in accuracy.

The method effectively handles data heterogeneity among clients.

Experimental results show improved convergence and model performance.

Abstract

Federated Learning (FL) presents an innovative approach to privacy-preserving distributed machine learning and enables efficient crowd intelligence on a large scale. However, a significant challenge arises when coordinating FL with crowd intelligence which diverse client groups possess disparate objectives due to data heterogeneity or distinct tasks. To address this challenge, we propose the Federated cINN Clustering Algorithm (FCCA) to robustly cluster clients into different groups, avoiding mutual interference between clients with data heterogeneity, and thereby enhancing the performance of the global model. Specifically, FCCA utilizes a global encoder to transform each client's private data into multivariate Gaussian distributions. It then employs a generative model to learn encoded latent features through maximum likelihood estimation, which eases optimization and avoids mode collapse. Finally, the central server collects converged local models to approximate similarities between clients and thus partition them into distinct clusters. Extensive experimental results demonstrate FCCA's superiority over other state-of-the-art clustered federated learning algorithms, evaluated on various models and datasets. These results suggest that our approach has substantial potential to enhance the efficiency and accuracy of real-world federated learning tasks.