采用模糊k核多粒度分解机制的高效社区发现  

Efficient community detection using fuzzy k-core multi-granularity decomposition mechanism

作　　者：李宏平 刘群[1] LI Hong-ping;LIU Qun(College of Computer Science and Technology,Chongqing University of Posts and Telecommunications,Chongqing 400000,China)

机构地区：[1]重庆邮电大学计算机科学与技术学院,重庆400000

出　　处：《计算机工程与设计》2022年第4期977-985,共9页Computer Engineering and Design

基　　金：国家自然科学基金项目(61772096)。

摘　　要：针对全局社区发现计算时间过长,以及k-core分解规则过于严格导致一些高重要性节点无法被保留的问题,提出基于模糊k-core的社区发现算法。采用基于模糊隶属度函数的模糊k-core分解思想,筛选出核心节点集,对由核心节点集所组成的子网进行局部社区划分,将核心子网的社区标签扩散到其余节点,完成全局社区发现。在标准数据集上的实验结果表明,算法在社区发现的精确度上保持了高水准,在大数据集上的运算时间显著降低。To solve the problems that the calculation time of global community detection is too long and the k-core decomposition rules are too strict for the community detection,a community detection algorithm based on fuzzy k-core was proposed.The fuzzy k-core decomposition idea was introduced based on fuzzy membership function to screen out the core node set.The subnet composed by the core node set was locally divided into communities,the community label of the core subnet was spread to other nodes,and the global community detection was finished.Experiments on real standard data sets show that the proposed algorithm excels in community detection and significantly reduces the computing time on large data sets.

关 键 词：社区发现 模糊k-core 隶属度函数 局部社区划分 标签传播 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]