Self-Supervised Discriminative Feature Learning for Deep Multi-View Clustering

TL;DR

This paper introduces SDMVC, a self-supervised deep learning method for multi-view clustering that effectively leverages complementary information and mitigates negative impacts from views with unclear structures, outperforming existing methods.

Contribution

The paper proposes a novel self-supervised discriminative feature learning approach for deep multi-view clustering that enhances clustering performance by integrating global features and a unified target distribution.

Findings

SDMVC outperforms 14 state-of-the-art methods on various datasets.

The method effectively handles views with unclear clustering structures.

Global discriminative features improve multi-view clustering accuracy.

Abstract

Multi-view clustering is an important research topic due to its capability to utilize complementary information from multiple views. However, there are few methods to consider the negative impact caused by certain views with unclear clustering structures, resulting in poor multi-view clustering performance. To address this drawback, we propose self-supervised discriminative feature learning for deep multi-view clustering (SDMVC). Concretely, deep autoencoders are applied to learn embedded features for each view independently. To leverage the multi-view complementary information, we concatenate all views' embedded features to form the global features, which can overcome the negative impact of some views' unclear clustering structures. In a self-supervised manner, pseudo-labels are obtained to build a unified target distribution to perform multi-view discriminative feature learning. During this process, global discriminative information can be mined to supervise all views to learn more discriminative features, which in turn are used to update the target distribution. Besides, this unified target distribution can make SDMVC learn consistent cluster assignments, which accomplishes the clustering consistency of multiple views while preserving their features' diversity. Experiments on various types of multi-view datasets show that SDMVC outperforms 14 competitors including classic and state-of-the-art methods. The code is available at https://github.com/SubmissionsIn/SDMVC.