基于协变量的一类贝叶斯社区检测算法  

A Class of Bayesian Community Detection Algorithms Based on Covariates

作　　者：冯丛慧 施三支[1] FENG Conghui;SHI Sanzhi(School of Mathematics and Statistics,Changchun University of Science and Technology,Changchun 130022)

机构地区：[1]长春理工大学数学与统计学院,长春130022

出　　处：《长春理工大学学报（自然科学版）》2024年第2期134-142,共9页Journal of Changchun University of Science and Technology(Natural Science Edition)

基　　金：国家自然科学基金(11601039);吉林省教育厅项目(JJKH20210809KJ)。

摘　　要：在复杂网络系统研究中,社区检测是挖掘网络数据内部结构信息的重要方法之一。提出了一个含有节点协变量信息的度修正随机块模型的贝叶斯社区检测算法,通过基于随机森林的算法选择重要的节点协变量,应用与协变量相关的随机划分模型划分社区隶属度,应用DCSBM模型,通过Gibbs采样方法进行社区检测并推断社区数量。数值模拟结果表明含有节点协变量信息的度修正随机块模型的贝叶斯社区检测算法可以显著提高社区检测的性能。最后将含有节点协变量信息的度修正随机块模型的贝叶斯社区检测算法方法应用到Weddell Sea营养网络的实际数据进行实证分析。In the study of complex network systems,community detection is one of the important methods to mine the internal structure information of network data.This paper proposes a Bayesian community detection algorithm for a Degree-corrected Stochastic Block Model containing node covariate information,by selecting important node covariates based on the Random Forest algorithm,applying a covariate-dependent random partition model divide the community membership,apply the DCSBM model,and use the Gibbs sampler method to detect the community structure and infer the number of communities.Numerical simulation results show that the Bayesian community detection algorithm for a Degree-corrected Stochastic Block Model containing node covariate information can significantly improve the performance of community detection.Finally,the Bayesian community detection algorithm for a Degree-corrected Stochastic Block Model containing node covariate information method is applied to the real data of the Weddell Sea trophic network for empirical analysis.

关 键 词：BAYES DCSBM 社区检测 随机森林算法 GIBBS采样 

分 类 号：O212[理学—概率论与数理统计]