Predicting Missing Links via Local Information - Physics > Data Analysis, Statistics and ProbabilityReportar como inadecuado




Predicting Missing Links via Local Information - Physics > Data Analysis, Statistics and Probability - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

Abstract: Missing link prediction of networks is of both theoretical interest andpractical significance in modern science. In this paper, we empiricallyinvestigate a simple framework of link prediction on the basis of nodesimilarity. We compare nine well-known local similarity measures on six realnetworks. The results indicate that the simplest measure, namely commonneighbors, has the best overall performance, and the Adamic-Adar index performsthe second best. A new similarity measure, motivated by the resource allocationprocess taking place on networks, is proposed and shown to have higherprediction accuracy than common neighbors. It is found that many links areassigned same scores if only the information of the nearest neighbors is used.We therefore design another new measure exploited information of the nextnearest neighbors, which can remarkably enhance the prediction accuracy.



Autor: Tao Zhou, Linyuan Lu, Yi-Cheng Zhang

Fuente: https://arxiv.org/



DESCARGAR PDF




Documentos relacionados