Learning Disentangled Representations for Generalized Multi-view Clustering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zou, Xin, Liu, Ruimeng, Tang, Chang, Li, Zhenglai, Liu, Xinwang, He, Kunlun, Li, Wanqing
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911687788986368
author Zou, Xin
Liu, Ruimeng
Tang, Chang
Li, Zhenglai
Liu, Xinwang
He, Kunlun
Li, Wanqing
author_facet Zou, Xin
Liu, Ruimeng
Tang, Chang
Li, Zhenglai
Liu, Xinwang
He, Kunlun
Li, Wanqing
contents Multi-View Clustering (MVC) has gained significant attention for its ability to leverage complementary information across diverse views. However, existing deep MVC methods often struggle with view-distribution entanglement during cross-view fusion, which hampers the quality of the shared latent space and leads to suboptimal Figures. To address this issue, we propose the Generalized Multi-view Auto-Encoder (GMAE), a framework designed to preserve cross-view complementarity through disentangled representation learning. Specifically, GMAE employs dual-path autoencoders to decouple source features into view-specific and view-common embeddings, facilitating the discovery of clearer clustering structures. We further construct cross-view adversarial discriminators to guide view-specific encoders in capturing more discriminative features. By strategically modulating mutual information, GMAE effectively aligns distributions and prevents representation collapse, ensuring the generation of robust, non-trivial embeddings. Comprehensive experiments on 13 benchmark datasets demonstrate that GMAE consistently outperforms state-of-the-art methods in both complete and incomplete MVC tasks. Our code implementation is available at the repository: https://github.com/obananas/GMAE.
format Preprint
id arxiv_https___arxiv_org_abs_2605_15640
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning Disentangled Representations for Generalized Multi-view Clustering
Zou, Xin
Liu, Ruimeng
Tang, Chang
Li, Zhenglai
Liu, Xinwang
He, Kunlun
Li, Wanqing
Computer Vision and Pattern Recognition
Multi-View Clustering (MVC) has gained significant attention for its ability to leverage complementary information across diverse views. However, existing deep MVC methods often struggle with view-distribution entanglement during cross-view fusion, which hampers the quality of the shared latent space and leads to suboptimal Figures. To address this issue, we propose the Generalized Multi-view Auto-Encoder (GMAE), a framework designed to preserve cross-view complementarity through disentangled representation learning. Specifically, GMAE employs dual-path autoencoders to decouple source features into view-specific and view-common embeddings, facilitating the discovery of clearer clustering structures. We further construct cross-view adversarial discriminators to guide view-specific encoders in capturing more discriminative features. By strategically modulating mutual information, GMAE effectively aligns distributions and prevents representation collapse, ensuring the generation of robust, non-trivial embeddings. Comprehensive experiments on 13 benchmark datasets demonstrate that GMAE consistently outperforms state-of-the-art methods in both complete and incomplete MVC tasks. Our code implementation is available at the repository: https://github.com/obananas/GMAE.
title Learning Disentangled Representations for Generalized Multi-view Clustering
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.15640