Journal of Computer Applications ›› 2022, Vol. 42 ›› Issue (4): 1021-1028.DOI: 10.11772/j.issn.1001-9081.2021071275

• The 36 CCF National Conference of Computer Applications (CCF NCCA 2020) • Previous Articles    

Survey of clustering based on deep learning

Yongfeng DONG1,2,3, Yahan DENG1,2,3, Yao DONG1,2,3(), Yacong WANG1,2,3   

  1. 1.School of Artificial Intelligence,Hebei University of Technology,Tianjin 300401,China
    2.Hebei Province Key Laboratory of Big Data Calculation (Hebei University of Technology),Tianjin 300401,China
    3.Hebei Data Driven Industrial Intelligent Engineering Research Center (Hebei University of Technology),Tianjin 300401,China
  • Received:2021-07-16 Revised:2021-08-01 Accepted:2021-08-18 Online:2022-04-15 Published:2022-04-10
  • Contact: Yao DONG
  • About author:DONG Yongfeng, born in 1977, Ph. D., professor. His research interests include artificial intelligence, knowledge graph.
    DENG Yahan, born in 1997, M. S. candidate. Her research interests include knowledge graph, machine learning.
    WANG Yacong, born in 1998, M. S. candidate. Her research interests include recommender system, knowledge graph.
  • Supported by:
    Natural Science Foundation of Tianjin City(19JCZDJC40000);Beidou Technology Achievement Transformation and Industrialization Fund of Beihang University(BARI2001);Science and Technology Research Project of Hebei Province Colleges and Universities(QN2021213)

基于深度学习的聚类综述

董永峰1,2,3, 邓亚晗1,2,3, 董瑶1,2,3(), 王雅琮1,2,3   

  1. 1.河北工业大学 人工智能与数据科学学院, 天津 300401
    2.河北省大数据计算重点实验室(河北工业大学), 天津 300401
    3.河北省数据驱动工业智能工程研究中心(河北工业大学), 天津 300401
  • 通讯作者: 董瑶
  • 作者简介:董永峰(1977—),男,河北定州人,教授,博士,CCF会员,主要研究方向:人工智能、知识图谱
    邓亚晗(1997—),女,广东新会人,硕士研究生,CCF会员,主要研究方向:知识图谱、机器学习
    王雅琮(1998—),女,河北石家庄人,硕士研究生,主要研究方向:推荐系统、知识图谱。
  • 基金资助:
    天津市自然科学基金资助项目(19JCZDJC40000);北航北斗技术成果转化及产业化资金资助项目(BARI2001);河北省高等学校科学技术研究项目(QN2021213)

Abstract:

Clustering is a technique to find the internal structure between data, which is a basic problem in many data-driven applications. Clustering performance depends largely on the quality of data representation. In recent years, deep learning is widely used in clustering tasks due to its powerful feature extraction ability, in order to learn better feature representation and improve clustering performance significantly. Firstly, the traditional clustering tasks were introduced. Then, the representative clustering methods based on deep learning were introduced according to the network structure, the existing problems were pointed out, and the applications of deep learning based clustering in different fields were presented. At last, the development of deep learning based clustering was summarized and prospected.

Key words: clustering, deep learning, graph clustering, feature representation, network architecture

摘要:

聚类是一种寻找数据之间内在结构的技术,是许多数据驱动应用领域的一个基本问题,而聚类性能在很大程度上取决于数据表示的质量。近年来,深度学习因其强大的特征提取能力被广泛地应用于聚类任务,以学习更好的特征表示,显著提高了聚类性能。首先,介绍了传统的聚类任务;然后,根据网络结构介绍了基于深度学习的聚类及代表性方法,指出了当前存在的问题,并介绍了基于深度学习的聚类在不同领域的应用;最后,对基于深度学习的聚类发展进行了总结与展望。

关键词: 聚类, 深度学习, 图聚类, 特征表示, 网络结构

CLC Number: