异质网络社区发现方法研究综述  

Survey of community discovery method of heterogeneous network

作　　者：周万珍[1] 宋健 许云峰[1] ZHOU Wanzhen;SONG Jian;XU Yunfeng(School of Information Science and Engineering,Hebei University of Science and Technology,Shijiazhuang,Hebei 050018,China)

机构地区：[1]河北科技大学信息科学与工程学院,河北石家庄050018

出　　处：《河北科技大学学报》2021年第3期231-240,共10页Journal of Hebei University of Science and Technology

基　　金：中国留学基金委地方合作项目(201808130283);教育部人工智能协同育人项目(201801003011);河北科技大学校立课题(82/1182108);河北科技大学雾霾与空气污染防治科研项目(82/1182169)。

摘　　要：社区结构是复杂网络研究中的重要领域,也是复杂网络的重要特征之一,发现网络中的社区结构在理解网络功能方面起着重要作用。通过对国内外异质网络社区发现文献进行深入研究,较为全面地对现有异质网络社区发现算法进行了归纳总结。首先,通过对国内外异质网络社区发现文献进行归纳,给出异质网络社区发现的基本概述,明确异质网络社区发现领域相关问题的基本定义。其次,介绍了异质网络社区发现算法及主要评价指标,利用不同网络结构以及算法对现有方法进行分类概述。最后,对异质网络社区发现算法的发展趋势进行了总结与展望,提出未来可以将研究重点集中在以下几个方面:1)探索基于异质网络的社区发现评价标准,以推动该领域的快速发展;2)设计更加通用的算法模型,解决由先验知识引起的未知社区数量问题;3)开展更多关于动态网络的研究。Community structure is an important field in the research of complex networks,and it is also one of the important characteristics of complex networks.It is found that the community structure in the network plays an important role in understanding network functions.Through in-depth research on the literature of heterogeneous network community discovery at home and abroad,a more comprehensive summary of the existing heterogeneous network community discovery algorithm is carried out.Firstly,by summarizing the literature of heterogeneous network community discovery at home and abroad,the basic overview of heterogeneous network community discovery is given,and the basic definition of related issues in the field of heterogeneous network community discovery is defined.Then,it introduces the heterogeneous network community discovery algorithm and the main evaluation index,and classifies the existing methods by using different network structures and algorithms.Finally,the development trend of heterogeneous network community discovery algorithms is summarized and prospected,and the future research focus can be focused on the following aspects:1)Exploring the evaluation criteria of community discovery based on heterogeneous networks to promote the rapid development of this field Development;2)Design a more general algorithm model to solve the problem of the number of unknown communities caused by prior knowledge;3)Carry out more research on dynamic networks.

关 键 词：计算机神经网络 复杂网络 社区发现 异质网络 图神经网络 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]