基于不同学习范式的深度图聚类方法综述  

A Survey of Deep Graph Clustering Methods Based on Different Learning Paradigms

作　　者：周丽娟[1] 吴梦琪 李欣冉 牛常勇[1] ZHOU Lijuan;WU Mengqi;LI Xinran;NIU Changyong(School of Computer Science and Artificial Intelligence,Zheng-zhou University,Zhengzhou 450001)

机构地区：[1]郑州大学计算机与人工智能学院,郑州450001

出　　处：《模式识别与人工智能》2025年第3期233-251,共19页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金项目(No.62006211)资助。

摘　　要：图聚类方法旨在使用无监督方式将图节点划分到不同类别中,用于发现复杂系统中的隐藏模式、社区结构和组织关系.现有方法通过不同的学习范式构建自监督模式,指导图表示学习并实现聚类,因此学习范式是图聚类方法的关键,但现有综述少有从学习范式的角度讨论图聚类方法.因此,文中基于不同学习范式总结图聚类方法的研究进展,将图聚类方法分类为重构式图聚类、对比式图聚类、对抗式图聚类和混合式图聚类.基于研究范围和聚类效果,重点探讨重构式图聚类和对比式图聚类.在单关系数据集和多关系数据集上的聚类结果表明,对比式图聚类在单关系数据集上表现较优,而重构式图聚类在多关系数据集上表现较优.最后,总结图聚类领域面临的挑战,展望未来的研究方向,并介绍深度图聚类方法在各个领域的应用.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.

关 键 词：图聚类 自监督训练 图神经网络 图对比学习 图重构学习 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]