A deep multiple self-supervised clustering model based on autoencoder networks

Abstract Numerous models for deep clustering have been proposed in recent times, exhibiting remarkable performance in unsupervised learning. However, they often concentrate on the features of the data itself, seldom taking into account the structure and distribution of the data during representation...

Full description

Saved in:
Bibliographic Details
Main Authors: Ling Zhu, Zijin Liu, Guangyu Liu
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-00349-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849704192377094144
author Ling Zhu
Zijin Liu
Guangyu Liu
author_facet Ling Zhu
Zijin Liu
Guangyu Liu
author_sort Ling Zhu
collection DOAJ
description Abstract Numerous models for deep clustering have been proposed in recent times, exhibiting remarkable performance in unsupervised learning. However, they often concentrate on the features of the data itself, seldom taking into account the structure and distribution of the data during representation learning. To address this challenge, we propose a new Deep Multiple Self-supervised Clustering model, termed DMSC, which places greater emphasis on the structural distribution of the data. The proposed model effectively integrates the advantages of autoencoder and fuzzy C-Means clustering, performing multi-level clustering evaluations throughout multiple iterations of the autoencoder network training process. It leverages a gradient-like approach for data reconstruction, enabling the autoencoder to learn features more conducive to clustering, thereby enhancing clustering performance. The experimental results show that the model performs significantly better than various common clustering algorithms on datasets of different types in multiple fields. Furthermore, to boost the efficiency of the multi-layer clustering module within our model and minimize algorithmic overhead, we integrate a distance-based Two-stage fuzzy C-Means clustering method. This approach introduces an efficient, adaptable, and rational technique for initializing cluster centers and membership matrices for fuzzy C-Means clustering, achieving convergence of the loss function in a shorter time frame. Compared to the performance of traditional fuzzy C-Means clustering algorithms on various public datasets, our proposed method significantly reduces computation time and noticeably improves iteration efficiency.
format Article
id doaj-art-c1d5e1f26b1f4cb5b3ed76546df3d779
institution DOAJ
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-c1d5e1f26b1f4cb5b3ed76546df3d7792025-08-20T03:16:51ZengNature PortfolioScientific Reports2045-23222025-05-0115111410.1038/s41598-025-00349-zA deep multiple self-supervised clustering model based on autoencoder networksLing Zhu0Zijin Liu1Guangyu Liu2School of Information Technology and Artificial Intelligence, Zhejiang University of Finance and EconomicsSchool of Information Technology and Artificial Intelligence, Zhejiang University of Finance and EconomicsKey Laboratory of IoT and Information Fusion Technology of Zhejiang Province and School of Automation, Hangzhou Dianzi UniversityAbstract Numerous models for deep clustering have been proposed in recent times, exhibiting remarkable performance in unsupervised learning. However, they often concentrate on the features of the data itself, seldom taking into account the structure and distribution of the data during representation learning. To address this challenge, we propose a new Deep Multiple Self-supervised Clustering model, termed DMSC, which places greater emphasis on the structural distribution of the data. The proposed model effectively integrates the advantages of autoencoder and fuzzy C-Means clustering, performing multi-level clustering evaluations throughout multiple iterations of the autoencoder network training process. It leverages a gradient-like approach for data reconstruction, enabling the autoencoder to learn features more conducive to clustering, thereby enhancing clustering performance. The experimental results show that the model performs significantly better than various common clustering algorithms on datasets of different types in multiple fields. Furthermore, to boost the efficiency of the multi-layer clustering module within our model and minimize algorithmic overhead, we integrate a distance-based Two-stage fuzzy C-Means clustering method. This approach introduces an efficient, adaptable, and rational technique for initializing cluster centers and membership matrices for fuzzy C-Means clustering, achieving convergence of the loss function in a shorter time frame. Compared to the performance of traditional fuzzy C-Means clustering algorithms on various public datasets, our proposed method significantly reduces computation time and noticeably improves iteration efficiency.https://doi.org/10.1038/s41598-025-00349-zDeep clusteringAutoencoderFuzzy C-means clustering
spellingShingle Ling Zhu
Zijin Liu
Guangyu Liu
A deep multiple self-supervised clustering model based on autoencoder networks
Scientific Reports
Deep clustering
Autoencoder
Fuzzy C-means clustering
title A deep multiple self-supervised clustering model based on autoencoder networks
title_full A deep multiple self-supervised clustering model based on autoencoder networks
title_fullStr A deep multiple self-supervised clustering model based on autoencoder networks
title_full_unstemmed A deep multiple self-supervised clustering model based on autoencoder networks
title_short A deep multiple self-supervised clustering model based on autoencoder networks
title_sort deep multiple self supervised clustering model based on autoencoder networks
topic Deep clustering
Autoencoder
Fuzzy C-means clustering
url https://doi.org/10.1038/s41598-025-00349-z
work_keys_str_mv AT lingzhu adeepmultipleselfsupervisedclusteringmodelbasedonautoencodernetworks
AT zijinliu adeepmultipleselfsupervisedclusteringmodelbasedonautoencodernetworks
AT guangyuliu adeepmultipleselfsupervisedclusteringmodelbasedonautoencodernetworks
AT lingzhu deepmultipleselfsupervisedclusteringmodelbasedonautoencodernetworks
AT zijinliu deepmultipleselfsupervisedclusteringmodelbasedonautoencodernetworks
AT guangyuliu deepmultipleselfsupervisedclusteringmodelbasedonautoencodernetworks