Generative Diffusion Contrastive Network for Multi-View Clustering

Jian Zhu

doi:10.1109/LSP.2026.3668750

Generative Diffusion Contrastive Network for Multi-View Clustering

2026-02-27

0

PRE

AI

DOI：10.1109/LSP.2026.3668750

Original

Original request for help

Save

Abstract

En 中文

In recent years, Multi-View Clustering (MVC) has been significantly advanced under the influence of deep learning. By integrating heterogeneous data from multiple views, MVC enhances clustering analysis, making multi-view fusion critical toclustering performance. However, multi-view fusion remains challenged by low-quality data, primarily stemming from tworeasons: 1) Certain views are contaminated by noisy data. 2) Some views suffer from missing data. This paper proposes anovel Stochastic Generative Diffusion Fusion (SGDF) method to address this problem. SGDF leverages a multiple generative mechanism for the multi-view feature of each sample. It exhibits robustness against low-quality data. Building on SGDF, wefurther present the Generative Diffusion Contrastive Network (GDCN). Extensive experiments show that GDCN achieves the state-of-the-art results in deep MVC tasks.

Keywords:

Deep clustering

diffusion model

multi-view clustering

multi-view fusion

Generative Diffusion Contrastive Network for Multi-View Clustering

Abstract

Journal

Organization