基于随机游动的近似主题搜索方法

超链接诱导主题搜索(hyperlink induced topic search,HITS)是当前最具权威性和使用最广泛的图上节点个性化排名算法。HITS算法通过线性迭代的方式计算图上节点的排名,计算复杂度高,因此不能满足大量的用户实时请求。通过随机游动的思想对HITS方法进行建模分析,利用蒙特卡洛的采样方法对节点的HITS排名进行估算,提出了基于蒙特卡洛思想的节点HITS排名近似算法。理论分析和实验表明,提出的随机游动近似HITS方法不但执行效率高,而且具有很高的准确性,明显优于现有的相关研究。...

Full description

Saved in:
Bibliographic Details
Published in计算机应用研究 Vol. 32; no. 3; pp. 759 - 763
Main Author 张凌晓 路新华 刘克成
Format Journal Article
LanguageChinese
Published 南阳理工学院计算机与信息工程学院,河南南阳,473004%南阳理工学院计算机与信息工程学院,河南南阳473004 2015
郑州大学信息工程学院,郑州450002
Subjects
Online AccessGet full text
ISSN1001-3695
DOI10.3969/j.issn.1001-3695.2015.03.027

Cover

More Information
Summary:超链接诱导主题搜索(hyperlink induced topic search,HITS)是当前最具权威性和使用最广泛的图上节点个性化排名算法。HITS算法通过线性迭代的方式计算图上节点的排名,计算复杂度高,因此不能满足大量的用户实时请求。通过随机游动的思想对HITS方法进行建模分析,利用蒙特卡洛的采样方法对节点的HITS排名进行估算,提出了基于蒙特卡洛思想的节点HITS排名近似算法。理论分析和实验表明,提出的随机游动近似HITS方法不但执行效率高,而且具有很高的准确性,明显优于现有的相关研究。
Bibliography:51-1196/TP
Hyperlink induced topic search(HITS) is one of the most authoritative and widely used personalized ranking algo- rithm on graphs. The HITS algorithm ranks nodes on graphs according to power iteration, and has high complexity of computa- tion. In order to improve computation time, this paper analyzed and modeled the HITS algorithm with the random walk ap- proach, and proposed Monte Carlo based approximation computation algorithms for the HITS ranking. Theoretical analysis and experiments show that the proposed random walk based approach of HITS ranking is not only efficient, but also has higher ac- curacy, and is significantly better than related works.
ZHANG Llng-xiao , LU Xin-hua, LIU Ke-cheng (1. School of Computer & Information Engineering, Nanyang Institute of Technology, Nanyang Henan 473004, China; 2. College of Informa- tion Engineering, Zhengzhou University, Zhengzhou 450002, China)
vsocial network ; graph ; influence ; ranking ; random walk ; Monte Carlo method
ISSN:1001-3695
DOI:10.3969/j.issn.1001-3695.2015.03.027