Federated Deep Subspace Clustering

TL;DR

This paper presents FDSC, a federated deep subspace clustering method that preserves local data relationships and improves clustering performance while maintaining data privacy across clients.

Contribution

The paper introduces a novel federated learning framework for deep subspace clustering that incorporates local neighborhood preservation for enhanced accuracy.

Findings

FDSC outperforms existing clustering methods on public datasets.

Local neighborhood preservation improves clustering quality.

Federated approach maintains data privacy effectively.

Abstract

This paper introduces FDSC, a private-protected subspace clustering (SC) approach with federated learning (FC) schema. In each client, there is a deep subspace clustering network accounting for grouping the isolated data, composed of a encode network, a self-expressive layer, and a decode network. FDSC is achieved by uploading the encode network to communicate with other clients in the server. Besides, FDSC is also enhanced by preserving the local neighborhood relationship in each client. With the effects of federated learning and locality preservation, the learned data features from the encoder are boosted so as to enhance the self-expressiveness learning and result in better clustering performance. Experiments test FDSC on public datasets and compare with other clustering methods, demonstrating the effectiveness of FDSC.