Privacy-Preserving Federated Deep Clustering based on GAN

TL;DR

This paper introduces a novel federated clustering method that uses GANs to generate synthetic data, enabling privacy-preserving, effective clustering in distributed, high-dimensional data settings without sharing private data.

Contribution

The paper proposes a new federated deep clustering approach using GANs, addressing non-IID data challenges and enhancing privacy guarantees in federated learning.

Findings

Effective clustering accuracy demonstrated on multiple datasets

GAN-generated data preserves privacy while enabling clustering

Outperforms traditional federated clustering methods

Abstract

Federated clustering (FC) is an essential extension of centralized clustering designed for the federated setting, wherein the challenge lies in constructing a global similarity measure without the need to share private data. Conventional approaches to FC typically adopt extensions of centralized methods, like K-means and fuzzy c-means. However, these methods are susceptible to non-independent-and-identically-distributed (non-IID) data among clients, leading to suboptimal performance, particularly with high-dimensional data. In this paper, we present a novel approach to address these limitations by proposing a Privacy-Preserving Federated Deep Clustering based on Generative Adversarial Networks (GANs). Each client trains a local generative adversarial network (GAN) locally and uploads the synthetic data to the server. The server applies a deep clustering network on the synthetic data to establish $k$ cluster centroids, which are then downloaded to the clients for cluster assignment. Theoretical analysis demonstrates that the GAN-generated samples, shared among clients, inherently uphold certain privacy guarantees, safeguarding the confidentiality of individual data. Furthermore, extensive experimental evaluations showcase the effectiveness and utility of our proposed method in achieving accurate and privacy-preserving federated clustering.