Federated Deep Subspace Clustering
This work addresses privacy concerns in clustering for distributed data scenarios, but it appears incremental as it combines existing techniques like federated learning and deep subspace clustering.
The paper tackles the problem of subspace clustering in a federated learning setting to protect data privacy, resulting in improved clustering performance through locality preservation and federated communication.
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.