Link prediction based on community division and resource allocation

被引：0
作者：
Xu, Xiaowei [1 ]
Jin, Gaofang [1 ]
Li, Li [1 ]
机构：
[1] Faculty of Computer and Information Science, Southwest University, Chongqing
来源：
Journal of Computational Information Systems | 2014年 / 10卷 / 17期
关键词：
Clique percolation; Credibility score; Network topology; Probability distribution; Resource allocation;
D O I：
10.12733/jcis11691
中图分类号：
学科分类号：
摘要：
Recent work in complex network and social network communities has been devoted to link prediction. Link prediction in complex network is based on the probability or the weight of the edge connecting two nodes in the network. It is useful to predict the missing edge or identify the spurious edge. In this paper, a novel link prediction method based on community division and resource allocation is presented. Clique percolation algorithms are applied to divide the network into overlapping communities and simplify the network model. The credibility score of each pair of nodes is computed by accumulating the scores in and between communities in which the nodes belong to. Resource allocation plays an important role in the computation of credibility scores. We evaluate the approach on different network topologies and edge probability distributions. The experimental results show that our approach works well. We achieved AUC 0.94 on USAir data set. Different topologies can indeed benefit from the proposed community division and resource allocation approach. Copyright © 2014 Binary Information Press.
引用
收藏
页码：7661 / 7668
页数：7
相关论文
共 7 条
  • [1] Hong W., Weihua Y., Xiaomei Y., Bi-direction Link Prediction in Dynamic Multi-dimension Networks, Journal of Computational Information Systems, 10, 3, pp. 1333-1340, (2014)
  • [2] Liben-Nowell D., Kleinberg J., The link-prediction problem for social networks, J Am Soc Inform Sci Technol, 58, 7, pp. 1019-1031, (2007)
  • [3] Clauset A., Moore C., Newman M.E.J., Hierarchical structure and the prediction of missing links in networks, Nature, 453, pp. 98-101, (2008)
  • [4] Wang X., Et al., Complex Network Theory and Its Application, (2005)
  • [5] Link Prediction on Complex Networks, Journal of University of Electronic Science and Technology of China, 39, 5, (2010)
  • [6] Hanely J.A., Mcneil B.J., The meaning and use of the area under a receiver operating characteristic (ROC) curve, Radiology, 143, pp. 29-36, (1982)
  • [7] Zhou T., Ren J., Medo M., Et al., Bipartite network projection and personal recommendation, Phys Rev E, 76, (2007)
1