One-Shot Hierarchical Federated Clustering

TL;DR

This paper proposes a novel one-shot hierarchical federated clustering framework that efficiently explores and aggregates complex, multi-granular client distributions while preserving privacy, outperforming existing methods on multiple datasets.

Contribution

It introduces a one-shot hierarchical federated clustering method with client-end distribution exploration and server-end multi-granular fusion, addressing computational and privacy challenges.

Findings

Outperforms state-of-the-art federated clustering methods.

Effectively explores complex, multi-granular cluster distributions.

Demonstrates robustness across ten public datasets.

Abstract

Driven by the growth of Web-scale decentralized services, Federated Clustering (FC) aims to extract knowledge from heterogeneous clients in an unsupervised manner while preserving the clients' privacy, which has emerged as a significant challenge due to the lack of label guidance and the Non-Independent and Identically Distributed (non-IID) nature of clients. In real scenarios such as personalized recommendation and cross-device user profiling, the global cluster may be fragmented and distributed among different clients, and the clusters may exist at different granularities or even nested. Although Hierarchical Clustering (HC) is considered promising for exploring such distributions, the sophisticated recursive clustering process makes it more computationally expensive and vulnerable to privacy exposure, thus relatively unexplored under the federated learning scenario. This paper introduces an efficient one-shot hierarchical FC framework that performs client-end distribution exploration and server-end distribution aggregation through one-way prototype-level communication from clients to the server. A fine partition mechanism is developed to generate successive clusterlets to describe the complex landscape of the clients' clusters. Then, a multi-granular learning mechanism on the server is proposed to fuse the clusterlets, even when they have inconsistent granularities generated from different clients. It turns out that the complex cluster distributions across clients can be efficiently explored, and extensive experiments comparing state-of-the-art methods on ten public datasets demonstrate the superiority of the proposed method.