A new type of federated clustering: A non-model-sharing approach

TL;DR

This paper introduces DC-Clustering, a federated clustering method that enables privacy-preserving, efficient, and flexible clustering over complex distributed data without sharing raw data, suitable for sensitive domains.

Contribution

It proposes a novel federated clustering approach supporting complex data splits, sharing only intermediate representations, and achieving high performance with minimal communication.

Findings

Achieves clustering performance comparable to centralized methods.

Supports complex data partitioning scenarios with horizontal and vertical splits.

Requires only a single communication round.

Abstract

In recent years, the growing need to leverage sensitive data across institutions has led to increased attention on federated learning (FL), a decentralized machine learning paradigm that enables model training without sharing raw data. However, existing FL-based clustering methods, known as federated clustering, typically assume simple data partitioning scenarios such as horizontal or vertical splits, and cannot handle more complex distributed structures. This study proposes data collaboration clustering (DC-Clustering), a novel federated clustering method that supports clustering over complex data partitioning scenarios where horizontal and vertical splits coexist. In DC-Clustering, each institution shares only intermediate representations instead of raw data, ensuring privacy preservation while enabling collaborative clustering. The method allows flexible selection between k-means and spectral clustering, and achieves final results with a single round of communication with the central server. We conducted extensive experiments using synthetic and open benchmark datasets. The results show that our method achieves clustering performance comparable to centralized clustering where all data are pooled. DC-Clustering addresses an important gap in current FL research by enabling effective knowledge discovery from distributed heterogeneous data. Its practical properties -- privacy preservation, communication efficiency, and flexibility -- make it a promising tool for privacy-sensitive domains such as healthcare and finance.