Generative Diffusion Contrastive Network for Multi-View Clustering

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhu, Jian, Zou, Xin, Wang, Xi, Liu, Lei, Tang, Chang, Dai, Li-Rong
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915737360138240
author Zhu, Jian
Zou, Xin
Wang, Xi
Liu, Lei
Tang, Chang
Dai, Li-Rong
author_facet Zhu, Jian
Zou, Xin
Wang, Xi
Liu, Lei
Tang, Chang
Dai, Li-Rong
contents 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 to clustering performance. However, there is a problem of low-quality data in multi-view fusion. This problem primarily arises from two reasons: 1) Certain views are contaminated by noisy data. 2) Some views suffer from missing data. This paper proposes a novel 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 is robust to low-quality data. Building on SGDF, we further present the Generative Diffusion Contrastive Network (GDCN). Extensive experiments show that GDCN achieves the state-of-the-art results in deep MVC tasks. The source code is publicly available at https://github.com/HackerHyper/GDCN.
format Preprint
id arxiv_https___arxiv_org_abs_2509_09527
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generative Diffusion Contrastive Network for Multi-View Clustering
Zhu, Jian
Zou, Xin
Wang, Xi
Liu, Lei
Tang, Chang
Dai, Li-Rong
Computer Vision and Pattern Recognition
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 to clustering performance. However, there is a problem of low-quality data in multi-view fusion. This problem primarily arises from two reasons: 1) Certain views are contaminated by noisy data. 2) Some views suffer from missing data. This paper proposes a novel 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 is robust to low-quality data. Building on SGDF, we further present the Generative Diffusion Contrastive Network (GDCN). Extensive experiments show that GDCN achieves the state-of-the-art results in deep MVC tasks. The source code is publicly available at https://github.com/HackerHyper/GDCN.
title Generative Diffusion Contrastive Network for Multi-View Clustering
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.09527