MoEGCL: Mixture of Ego-Graphs Contrastive Representation Learning for Multi-View Clustering

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhu, Jian, Zou, Xin, Sun, Jun, Luo, Cheng, Liu, Lei, Zeng, Lingfang, Zhang, Ning, Wu, Bian, Tang, Chang, Dai, Lirong
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908907896569856
author Zhu, Jian
Zou, Xin
Sun, Jun
Luo, Cheng
Liu, Lei
Zeng, Lingfang
Zhang, Ning
Wu, Bian
Tang, Chang
Dai, Lirong
author_facet Zhu, Jian
Zou, Xin
Sun, Jun
Luo, Cheng
Liu, Lei
Zeng, Lingfang
Zhang, Ning
Wu, Bian
Tang, Chang
Dai, Lirong
contents In recent years, the advancement of Graph Neural Networks (GNNs) has significantly propelled progress in Multi-View Clustering (MVC). However, existing methods face the problem of coarse-grained graph fusion. Specifically, current approaches typically generate a separate graph structure for each view and then perform weighted fusion of graph structures at the view level, which is a relatively rough strategy. To address this limitation, we present a novel Mixture of Ego-Graphs Contrastive Representation Learning (MoEGCL). It mainly consists of two modules. In particular, we propose an innovative Mixture of Ego-Graphs Fusion (MoEGF), which constructs ego graphs and utilizes a Mixture-of-Experts network to implement fine-grained fusion of ego graphs at the sample level, rather than the conventional view-level fusion. Additionally, we present the Ego Graph Contrastive Learning (EGCL) module to align the fused representation with the view-specific representation. The EGCL module enhances the representation similarity of samples from the same cluster, not merely from the same sample, further boosting fine-grained graph representation. Extensive experiments demonstrate that MoEGCL achieves state-of-the-art results in deep multi-view clustering tasks. The source code is publicly available at https://github.com/HackerHyper/MoEGCL.
format Preprint
id arxiv_https___arxiv_org_abs_2511_05876
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MoEGCL: Mixture of Ego-Graphs Contrastive Representation Learning for Multi-View Clustering
Zhu, Jian
Zou, Xin
Sun, Jun
Luo, Cheng
Liu, Lei
Zeng, Lingfang
Zhang, Ning
Wu, Bian
Tang, Chang
Dai, Lirong
Computer Vision and Pattern Recognition
Machine Learning
In recent years, the advancement of Graph Neural Networks (GNNs) has significantly propelled progress in Multi-View Clustering (MVC). However, existing methods face the problem of coarse-grained graph fusion. Specifically, current approaches typically generate a separate graph structure for each view and then perform weighted fusion of graph structures at the view level, which is a relatively rough strategy. To address this limitation, we present a novel Mixture of Ego-Graphs Contrastive Representation Learning (MoEGCL). It mainly consists of two modules. In particular, we propose an innovative Mixture of Ego-Graphs Fusion (MoEGF), which constructs ego graphs and utilizes a Mixture-of-Experts network to implement fine-grained fusion of ego graphs at the sample level, rather than the conventional view-level fusion. Additionally, we present the Ego Graph Contrastive Learning (EGCL) module to align the fused representation with the view-specific representation. The EGCL module enhances the representation similarity of samples from the same cluster, not merely from the same sample, further boosting fine-grained graph representation. Extensive experiments demonstrate that MoEGCL achieves state-of-the-art results in deep multi-view clustering tasks. The source code is publicly available at https://github.com/HackerHyper/MoEGCL.
title MoEGCL: Mixture of Ego-Graphs Contrastive Representation Learning for Multi-View Clustering
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2511.05876