Asymmetric double-winged multi-view clustering network for exploring Diverse and Consistent Information

TL;DR

This paper introduces CodingNet, a novel multi-view clustering network that simultaneously explores diverse shallow features and consistent deep features, improving clustering performance in unsupervised multi-view data analysis.

Contribution

The paper proposes an asymmetric network structure and a dual contrastive mechanism to effectively capture both diverse and consistent information in multi-view clustering.

Findings

Outperforms most state-of-the-art algorithms on six benchmark datasets.

Effectively extracts and utilizes both shallow and deep features.

Enhances clustering accuracy by balancing diversity and consistency.

Abstract

In unsupervised scenarios, deep contrastive multi-view clustering (DCMVC) is becoming a hot research spot, which aims to mine the potential relationships between different views. Most existing DCMVC algorithms focus on exploring the consistency information for the deep semantic features, while ignoring the diverse information on shallow features. To fill this gap, we propose a novel multi-view clustering network termed CodingNet to explore the diverse and consistent information simultaneously in this paper. Specifically, instead of utilizing the conventional auto-encoder, we design an asymmetric structure network to extract shallow and deep features separately. Then, by aligning the similarity matrix on the shallow feature to the zero matrix, we ensure the diversity for the shallow features, thus offering a better description of multi-view data. Moreover, we propose a dual contrastive mechanism that maintains consistency for deep features at both view-feature and pseudo-label levels. Our framework's efficacy is validated through extensive experiments on six widely used benchmark datasets, outperforming most state-of-the-art multi-view clustering algorithms.