蜗牛分享 http://blog.sciencenet.cn/u/babyann519

博文

PNAS: 如何刻画网络的结构一致性及链路可预测性?

已有 12910 次阅读 2015-3-28 22:09 |个人分类:科研工作|系统分类:论文交流|关键词:链路预测,复杂网络,可预测性| 复杂网络, 链路预测, 可预测性

Significance

Quantifying a network's link predictability allows us to (i) evaluate predictive algorithms associated with the network, (ii) estimate the extent to which the organization of the network is explicable, and (iii) monitor sudden mechanistic changes during the network's evolution. The hypothesis of this paper is that a group of links is predictable if removing them has only a small effect on the network's structural features. We introduce a quantitative index for measuring link predictability and an algorithm that outperforms state-of-the-art link prediction methods in both accuracy and universality. This study provides fundamental insights into  important scientific problems and will aid in the development of information filtering technologies.

 

Abstract

The organization of real networks usuallyembodies both regularities and irregularities, and, in principle, the formercan be modeled. The extent to which the formation of a network can be explainedcoincides with our ability to predict missing links. To understand networkorganization, we should be able to estimate link predictability. We assume thatthe regularity of a network is reflected in the consistency of structuralfeatures before and after a random removal of a small set of links. Based on theperturbation of the adjacency matrix, we propose a universal structuralconsistency index that is free of prior knowledge of network organization.Extensive experiments on disparate real-world networks demonstrate that (i)structural consistency is a good estimation of link predictability and (ii) aderivative algorithm outperforms state-of-the-art link prediction methods inboth accuracy and robustness. This analysis has further applications inevaluating link prediction algorithms and monitoring sudden changes in evolvingnetwork mechanisms. It will provide unique fundamental insights into theabove-mentioned academic research fields, and will foster the development ofadvanced information filtering technologies of interest to informationtechnology practitioners.


全文下载地址(免费)

http://www.pnas.org/content/112/8/2325.full?sid=61535af6-9110-483a-9370-a9389abd7977


更多详情参见周涛老师博客~

http://blog.sciencenet.cn/home.php?mod=space&uid=3075&do=blog&id=867520

 




http://blog.sciencenet.cn/blog-329471-878035.html

上一篇:Physica A: 2014's Top-5 most downloaded articles 免费下载~
下一篇:推荐一个暑期学校——Joseph E. Stiglitz讲授

5 庄明浩 章忠志 杨正瓴 高建国 nextvisionary

该博文允许注册用户评论 请点击登录 评论 (3 个评论)

数据加载中...

Archiver|手机版|科学网 ( 京ICP备14006957 )

GMT+8, 2020-1-19 22:11

Powered by ScienceNet.cn

Copyright © 2007- 中国科学报社

返回顶部