Multiview Deep Autoencoder-Inspired Layerwise Error-Correcting Non-Negative Matrix Factorization

Multiview Clustering (MVC) plays a crucial role in the holistic analysis of complex data by leveraging complementary information from multiple perspectives, a necessity in the era of big data. Non-negative Matrix Factorization (NMF)-based methods have demonstrated their effectiveness and broad appli...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuan Liu, Yuan Wan, Zaili Yang, Huanhuan Li
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/9/1422
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850155756839501824
author Yuan Liu
Yuan Wan
Zaili Yang
Huanhuan Li
author_facet Yuan Liu
Yuan Wan
Zaili Yang
Huanhuan Li
author_sort Yuan Liu
collection DOAJ
description Multiview Clustering (MVC) plays a crucial role in the holistic analysis of complex data by leveraging complementary information from multiple perspectives, a necessity in the era of big data. Non-negative Matrix Factorization (NMF)-based methods have demonstrated their effectiveness and broad applicability in clustering tasks, as they generate meaningful attribute distributions and cluster assignments. However, existing shallow NMF approaches fail to capture the hierarchical structures inherent in real-world data, while deep NMF ones overlook the accumulation of reconstruction errors across layers by solely focusing on a global loss function. To address these limitations, this study aims to develop a novel method that integrates an autoencoder-inspired structure into the deep NMF framework, incorporating layerwise error-correcting constraints. This approach can facilitate the extraction of hierarchical features while effectively mitigating reconstruction error accumulation in deep architectures. Additionally, repulsion-attraction manifold learning is incorporated at each layer to preserve intrinsic geometric structures within the data. The proposed model is evaluated on five real-world multiview datasets, with experimental results demonstrating its effectiveness in capturing hierarchical representations and improving clustering performance.
format Article
id doaj-art-200cf25343da4a83ba2248e31b9b0537
institution OA Journals
issn 2227-7390
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-200cf25343da4a83ba2248e31b9b05372025-08-20T02:24:47ZengMDPI AGMathematics2227-73902025-04-01139142210.3390/math13091422Multiview Deep Autoencoder-Inspired Layerwise Error-Correcting Non-Negative Matrix FactorizationYuan Liu0Yuan Wan1Zaili Yang2Huanhuan Li3School of Mathematics and Statistics, Wuhan University of Technology, 122 Luoshi Road, Wuhan 430070, ChinaSchool of Mathematics and Statistics, Wuhan University of Technology, 122 Luoshi Road, Wuhan 430070, ChinaLiverpool Logistics, Offshore and Marine Research Institute, Liverpool John Moores University, Liverpool L3 3AF, UKLiverpool Logistics, Offshore and Marine Research Institute, Liverpool John Moores University, Liverpool L3 3AF, UKMultiview Clustering (MVC) plays a crucial role in the holistic analysis of complex data by leveraging complementary information from multiple perspectives, a necessity in the era of big data. Non-negative Matrix Factorization (NMF)-based methods have demonstrated their effectiveness and broad applicability in clustering tasks, as they generate meaningful attribute distributions and cluster assignments. However, existing shallow NMF approaches fail to capture the hierarchical structures inherent in real-world data, while deep NMF ones overlook the accumulation of reconstruction errors across layers by solely focusing on a global loss function. To address these limitations, this study aims to develop a novel method that integrates an autoencoder-inspired structure into the deep NMF framework, incorporating layerwise error-correcting constraints. This approach can facilitate the extraction of hierarchical features while effectively mitigating reconstruction error accumulation in deep architectures. Additionally, repulsion-attraction manifold learning is incorporated at each layer to preserve intrinsic geometric structures within the data. The proposed model is evaluated on five real-world multiview datasets, with experimental results demonstrating its effectiveness in capturing hierarchical representations and improving clustering performance.https://www.mdpi.com/2227-7390/13/9/1422multiview clustering (MVC)autoencoder-inspired structurenon-negative matrix factorization (NMF)geometric information
spellingShingle Yuan Liu
Yuan Wan
Zaili Yang
Huanhuan Li
Multiview Deep Autoencoder-Inspired Layerwise Error-Correcting Non-Negative Matrix Factorization
Mathematics
multiview clustering (MVC)
autoencoder-inspired structure
non-negative matrix factorization (NMF)
geometric information
title Multiview Deep Autoencoder-Inspired Layerwise Error-Correcting Non-Negative Matrix Factorization
title_full Multiview Deep Autoencoder-Inspired Layerwise Error-Correcting Non-Negative Matrix Factorization
title_fullStr Multiview Deep Autoencoder-Inspired Layerwise Error-Correcting Non-Negative Matrix Factorization
title_full_unstemmed Multiview Deep Autoencoder-Inspired Layerwise Error-Correcting Non-Negative Matrix Factorization
title_short Multiview Deep Autoencoder-Inspired Layerwise Error-Correcting Non-Negative Matrix Factorization
title_sort multiview deep autoencoder inspired layerwise error correcting non negative matrix factorization
topic multiview clustering (MVC)
autoencoder-inspired structure
non-negative matrix factorization (NMF)
geometric information
url https://www.mdpi.com/2227-7390/13/9/1422
work_keys_str_mv AT yuanliu multiviewdeepautoencoderinspiredlayerwiseerrorcorrectingnonnegativematrixfactorization
AT yuanwan multiviewdeepautoencoderinspiredlayerwiseerrorcorrectingnonnegativematrixfactorization
AT zailiyang multiviewdeepautoencoderinspiredlayerwiseerrorcorrectingnonnegativematrixfactorization
AT huanhuanli multiviewdeepautoencoderinspiredlayerwiseerrorcorrectingnonnegativematrixfactorization