模式识别与人工智能
Wednesday, Jul. 30, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
Pattern Recognition and Artificial Intelligence  2025, Vol. 38 Issue (3): 233-251    DOI: 10.16451/j.cnki.issn1003-6059.202503004
Surveys and Reviews Current Issue| Next Issue| Archive| Adv Search |
A Survey of Deep Graph Clustering Methods Based on Different Learning Paradigms
ZHOU Lijuan1, WU Mengqi1, LI Xinran1, NIU Changyong1
1. School of Computer Science and Artificial Intelligence, Zheng-zhou University, Zhengzhou 450001

Download: PDF (1023 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  Graph clustering aims to partition graph nodes into different categories in an unsupervised manner, facilitating the discovery of hidden patterns, community structures and organizational relationships within complex systems. Existing methods construct different self-supervised information through various learning paradigms to guide graph representation learning and promote clustering. Therefore, the learning paradigm is the key to clustering algorithms. However, few existing reviews discuss graph clustering from the perspective of different learning paradigms. In this paper, the research progress on graph clustering based on different learning paradigms is summarized. Clustering methods are classified into reconstructive graph clustering, contrastive graph clustering, adversarial graph clustering and hybrid graph clustering. Considering the research scope and clustering effect, reconstructive graph clustering and contrastive graph clustering are discussed in detail. Graph clustering results on single-relation and multi-relation datasets are compared. The results show that contrastive graph clustering performs better on single-relation datasets, while reconstructive graph clustering is more effective on multi-relation datasets. Finally, the challenges faced in the graph clustering field are summarized, and future research directions are pointed out as well. The applications of deep graph clustering across various domains are additionally introduced.
Key wordsGraph Clustering      Self-Supervised Training      Graph Neural Networks      Graph Contrastive Learning      Graph Reconstructive Learning     
Received: 24 December 2024     
ZTFLH: TP183  
Fund:National Natural Science Foundation of China(No.62006211)
Corresponding Authors: NIU Changyong, Ph.D., associate professor. His research interests include large-scale data management and analysis on cloud platforms, machine learning with a focus on deep learning algorithms and applications, and mobile terminal system development.   
About author:: ZHOU Lijuan, Ph.D., associate profe-ssor. Her research interests include computer vision, machine learning and multimodal processing.
WU Mengqi, Master student. Her research interests include data mining, attributed graph clustering and contrastive learning.
LI Xinran, Master student. His research interests include multimodal recommendation and machine learning.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
ZHOU Lijuan
WU Mengqi
LI Xinran
NIU Changyong
Cite this article:   
ZHOU Lijuan,WU Mengqi,LI Xinran等. A Survey of Deep Graph Clustering Methods Based on Different Learning Paradigms[J]. Pattern Recognition and Artificial Intelligence, 2025, 38(3): 233-251.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202503004      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2025/V38/I3/233
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn