Towards Federated Clustering: A Client-wise Private Graph Aggregation Framework

TL;DR

This paper introduces SPP-FGC, a privacy-preserving federated clustering framework that uses local structural graphs for secure knowledge sharing, achieving high accuracy without compromising data privacy.

Contribution

It proposes a novel graph-based federated clustering method that preserves privacy and offers both one-shot and iterative modes for different data types.

Findings

Achieves up to 10% improvement in clustering accuracy (NMI) over baselines.

Maintains provable privacy guarantees.

Effective on various data types, including images.

Abstract

Federated clustering addresses the critical challenge of extracting patterns from decentralized, unlabeled data. However, it is hampered by the flaw that current approaches are forced to accept a compromise between performance and privacy: \textit{transmitting embedding representations risks sensitive data leakage, while sharing only abstract cluster prototypes leads to diminished model accuracy}. To resolve this dilemma, we propose Structural Privacy-Preserving Federated Graph Clustering (SPP-FGC), a novel algorithm that innovatively leverages local structural graphs as the primary medium for privacy-preserving knowledge sharing, thus moving beyond the limitations of conventional techniques. Our framework operates on a clear client-server logic; on the client-side, each participant constructs a private structural graph that captures intrinsic data relationships, which the server then securely aggregates and aligns to form a comprehensive global graph from which a unified clustering structure is derived. The framework offers two distinct modes to suit different needs. SPP-FGC is designed as an efficient one-shot method that completes its task in a single communication round, ideal for rapid analysis. For more complex, unstructured data like images, SPP-FGC+ employs an iterative process where clients and the server collaboratively refine feature representations to achieve superior downstream performance. Extensive experiments demonstrate that our framework achieves state-of-the-art performance, improving clustering accuracy by up to 10\% (NMI) over federated baselines while maintaining provable privacy guarantees.