Triple-Stream Contrastive Deep Embedding Clustering via Semantic Structure

Aiyu Zheng, Jianghui Cai (), Haifeng Yang (), Yalin Xun and Xujun Zhao
Additional contact information
Aiyu Zheng: School of Electronic Information and Engineering, Taiyuan University of Science and Technology, Taiyuan 030024, China
Jianghui Cai: School of Electronic Information and Engineering, Taiyuan University of Science and Technology, Taiyuan 030024, China
Haifeng Yang: School of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan 030024, China
Yalin Xun: School of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan 030024, China
Xujun Zhao: School of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan 030024, China

Mathematics, 2025, vol. 13, issue 22, 1-26

Abstract: Deep neural network-based deep clustering has achieved remarkable success by unifying representation learning and clustering. However, conventional representation modules are typically not tailored for clustering, resulting in conflicting objectives that hinder the model’s ability to capture semantic structures with high intra-cluster cohesion and low inter-cluster separation. To overcome this limitation, we propose a novel framework called Triple-stream Contrastive Deep Embedding Clustering via Semantic Structure (TCSS). TCSS is composed of representation and clustering modules, with its innovation rooted in several key designs that ensure their synergistic interaction for modeling semantic structures. First, TCSS introduces a triple-stream input framework that processes the raw instance along with its limited and aggressive augmented views. This design enables a new triple-stream self-training clustering loss, which uncovers implicit cluster structures by contrasting the three input streams. Second, within this loss, a dynamic clustering structure factor is developed to represent the evolving semantic structure in the representation space, thereby constraining the clustering-prediction distribution. Third, TCSS integrates semantic structure-aware techniques, including a clustering-oriented negative sampling strategy and a triple-stream alignment scheme based on k-nearest neighbors and centroids, to refine semantic structures both locally and globally. Extensive experiments on five benchmark datasets demonstrate that TCSS outperforms state-of-the-art methods.

Keywords: deep clustering; triple-stream self-training clustering loss; clustering-oriented contrastive learning; clustering structure factor (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/22/3578/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/22/3578/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:22:p:3578-:d:1789829

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().