Single-Round Clustered Federated Learning via Data Collaboration Analysis for Non-IID Data

TL;DR

This paper introduces DC-CFL, a single-round federated learning framework that clusters clients and trains models efficiently under non-IID data conditions, reducing communication overhead.

Contribution

DC-CFL is the first to enable client clustering and model training in a single communication round using data collaboration analysis, improving practicality in constrained environments.

Findings

Achieves comparable accuracy to multi-round methods

Uses total variation distance for client similarity

Requires only one communication round

Abstract

Federated Learning (FL) enables distributed learning across multiple clients without sharing raw data. When statistical heterogeneity across clients is severe, Clustered Federated Learning (CFL) can improve performance by grouping similar clients and training cluster-wise models. However, most CFL approaches rely on multiple communication rounds for cluster estimation and model updates, which limits their practicality under tight constraints on communication rounds. We propose Data Collaboration-based Clustered Federated Learning (DC-CFL), a single-round framework that completes both client clustering and cluster-wise learning, using only the information shared in DC analysis. DC-CFL quantifies inter-client similarity via total variation distance between label distributions, estimates clusters using hierarchical clustering, and performs cluster-wise learning via DC analysis. Experiments on multiple open datasets under representative non-IID conditions show that DC-CFL achieves accuracy comparable to multi-round baselines while requiring only one communication round. These results indicate that DC-CFL is a practical alternative for collaborative AI model development when multiple communication rounds are impractical.