Clusterability-Based Assessment of Potentially Noisy Views for Multi-View Clustering

TL;DR

This paper introduces a novel multi-view clusterability score (MVCS) to assess and detect noisy views in multi-view data before clustering, improving robustness and performance.

Contribution

It proposes the first clusterability measure specifically designed for multi-view data, enabling pre-clustering noisy view analysis and detection.

Findings

MVCS effectively identifies noisy views that degrade clustering performance.

The proposed method outperforms existing single-view clusterability measures in noisy-view detection.

Experiments on real-world datasets confirm the importance of pre-clustering noisy view analysis.

Abstract

In multi-view clustering, the quality of different views may vary substantially, and low-quality or degraded views can impair overall clustering performance. However, existing studies mainly address this issue within the clustering process through view weighting or noise-robust optimization, while paying limited attention to data-level assessment before clustering. In this paper, we study the problem of pre-clustering noisy-view analysis in multi-view data from a clusterability perspective. To this end, we propose a Multi-View Clusterability Score (MVCS), which quantifies the strength of latent cluster-related structures in multi-view data through three complementary components: per-view structural clusterability, joint-space clusterability, and cross-view neighborhood consistency. To the best of our knowledge, this is the first clusterability score specifically designed for multi-view data. We further use it to perform potentially noisy view analysis and noisy-view detection before clustering. Extensive experiments on real-world datasets demonstrate that noisy views can significantly degrade clustering performance, and that, compared with existing clusterability measures designed for single-view data, the proposed method more effectively supports noisy-view analysis and detection.