基于邻层传播的相对重要节点挖掘方法  

Relatively Important Nodes Mining Method Based on Neighbor Layer Diffuse

作　　者：赵娜[1,2,3] 李杰 王剑 彭西阳[1] 景铭[1,2] 聂永杰 郁湧 ZHAO Na;LI Jie;WANG Jian;PENG Xi-yang;JING Ming;NIE Yong-jie;YU Yong(School of Software,Yunnan University,Kunming 650091;Key Laboratory in Software Engineering of Yunnan Province Yunnan University,Kunming 650091;Electric Power Research Institute of Yunnan Power Grid,Kunming 650217;College of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650504)

机构地区：[1]云南大学软件学院,昆明650091 [2]云南大学云南省软件工程重点实验室,昆明650091 [3]云南电网有限责任公司电力科学研究院,昆明650217 [4]昆明理工大学信息工程及自动化学院,昆明650504

出　　处：《电子科技大学学报》2021年第1期121-126,共6页Journal of University of Electronic Science and Technology of China

基　　金：国家重点研发计划(2018YFB2100100);国家自然科学基金(62066048);中国博士后科学基金(2020M673312);云南省科技厅面上项目(202001BB050063);云南省教育厅科学研究基金(2019J0010,2019J0008);昆明市卫健委项目(2020-09-04-112)的资助

摘　　要：目前针对复杂网络中相对重要节点的挖掘方法已有一些成果,但方法的效率和准确性仍有待提高。该文基于如下假设—如果一个节点具有某种特征的邻居节点越多,则该节点具有此特征的可能性越大——提出了一种基于邻层传播(NLD)的相对重要节点挖掘算法,并通过实验比较与分析,验证了该方法的准确性与适用性。At present,there have been some achievements in mining methods for relatively important nodes in complex networks,but the efficiency and accuracy of the methods still need to be improved.Based on the assumption that if a node has more neighbor nodes with certain characteristics,the more likely this node has such characteristics.This paper proposes a relatively important node mining algorithm based on neighbor layer diffuse(NLD),and verifies the accuracy and applicability of the method through experimental comparison and analysis.

关 键 词：复杂网络 邻层传播 相对重要性 相对重要节点 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]