Federated Deep Multi-View Clustering with Global Self-Supervision

TL;DR

This paper introduces a federated deep multi-view clustering method that effectively handles data heterogeneity, incompleteness, and privacy concerns across distributed devices, achieving superior clustering performance.

Contribution

It proposes a novel federated clustering approach with global self-supervision, sample alignment, and data extension techniques to address heterogeneity and data incompleteness.

Findings

Outperforms existing methods in federated multi-view clustering tasks.

Effectively manages data heterogeneity and incompleteness.

Demonstrates superior clustering accuracy in experiments.

Abstract

Federated multi-view clustering has the potential to learn a global clustering model from data distributed across multiple devices. In this setting, label information is unknown and data privacy must be preserved, leading to two major challenges. First, views on different clients often have feature heterogeneity, and mining their complementary cluster information is not trivial. Second, the storage and usage of data from multiple clients in a distributed environment can lead to incompleteness of multi-view data. To address these challenges, we propose a novel federated deep multi-view clustering method that can mine complementary cluster structures from multiple clients, while dealing with data incompleteness and privacy concerns. Specifically, in the server environment, we propose sample alignment and data extension techniques to explore the complementary cluster structures of multiple views. The server then distributes global prototypes and global pseudo-labels to each client as global self-supervised information. In the client environment, multiple clients use the global self-supervised information and deep autoencoders to learn view-specific cluster assignments and embedded features, which are then uploaded to the server for refining the global self-supervised information. Finally, the results of our extensive experiments demonstrate that our proposed method exhibits superior performance in addressing the challenges of incomplete multi-view data in distributed environments.