A Novel Approach for Effective Multi-View Clustering with Information-Theoretic Perspective

TL;DR

This paper introduces SUMVC, an information-theoretic multi-view clustering method that enhances consistency and reduces redundancy across views, backed by theoretical analysis and superior experimental results.

Contribution

It proposes a novel information-theoretic framework for multi-view clustering, including a new lower bound for sufficient representations and a reliable clustering method SCMVC.

Findings

SUMVC outperforms existing methods on multiple datasets.

Theoretical analysis shows reduced Bayes Error Rate.

Effective reduction of view redundancy.

Abstract

Multi-view clustering (MVC) is a popular technique for improving clustering performance using various data sources. However, existing methods primarily focus on acquiring consistent information while often neglecting the issue of redundancy across multiple views. This study presents a new approach called Sufficient Multi-View Clustering (SUMVC) that examines the multi-view clustering framework from an information-theoretic standpoint. Our proposed method consists of two parts. Firstly, we develop a simple and reliable multi-view clustering method SCMVC (simple consistent multi-view clustering) that employs variational analysis to generate consistent information. Secondly, we propose a sufficient representation lower bound to enhance consistent information and minimise unnecessary information among views. The proposed SUMVC method offers a promising solution to the problem of multi-view clustering and provides a new perspective for analyzing multi-view data. To verify the effectiveness of our model, we conducted a theoretical analysis based on the Bayes Error Rate, and experiments on multiple multi-view datasets demonstrate the superior performance of SUMVC.