Link prediction via more information and evaluation index

被引：0

作者：

Cao, Jie ^{[1
,2
]}

Li, Bentian ^{[1
]}

Gui, Xiangquan ^{[1
,2
]}

Lin, Yunxia ^{[3
]}

机构：

[1] School of Computer and Communication, Lanzhou University of Technology, Lanzhou

[2] Research Center of Engineering and Technology for Manufacturing Information of Gansu Province, Lanzhou University of Technology, Lanzhou

[3] School of Information Science and Engineering, Lanzhou University, Lanzhou

来源：

Journal of Information and Computational Science | 2015年 / 12卷 / 16期

关键词：

Evaluation index; Link prediction; Similarity index;

D O I：

10.12733/jics20106855

中图分类号：

TM72 [输配电技术];

学科分类号：

摘要：

Link prediction is an important content in the related fields of computer and network. Recently, the link prediction algorithm based on node similarity is the research hotspot. However, it is found that the outcome of single predictor has large deviations with the actual network. For this question, in this paper, we propose a similarity index by combining more information of network from ten kinds of existed algorithm. We compare ten well-known local similarity index on five kinds of real network datasets like USAir network, Power Grid network and so on. The experimental results show that the new index has a better accuracy and university than the current algorithms. Simultaneously, we also found that the evaluation measures of link prediction are partial and one-sided. We therefore design another new evaluation index considering the factors of time and accuracy, which can evaluate algorithm more comprehensively and scientifically. © 2015 by Binary Information Press

引用

页码：5957 / 5966

页数：9

共 19 条

[1]

Huang Z., Li X., Chen H., Link prediction approach to collaborative fltering, Proceedings of the 5th ACM/IEEE-CS Joint Conference on Digital Libraries, pp. 141-142, (2005)

[2]

Sarukkai R.R., Link prediction and path analysis using markov chains, Computer Networks, 33, 1-6, pp. 377-386, (2000)

[3]

Lin D., An information-theoretic definition of similarity, Proceedings of the 15th Intl. Conf. Mach. Learn., pp. 296-304, (1998)

[4]

O'madadhain J., Hutchins J., Smyth P., Prediction and ranking algorithms for event-based network data, Proceedings of the ACM SIGKDD 2005, pp. 23-30, (2005)

[5]

Papadimitriou A., Symeonidis P., Manolopoulos Y., Scalable link prediction in social networks based on local graph characteristics, 2012 Ninth International Conference on Information Technology: New Generations (ITNG), pp. 738-743, (2012)

[6]

Zhou T., Lu L., Zhang Y., Predicting missing links via local information, The European Physical Journal B, 71, 4, pp. 623-630, (2009)

[7]

Lu L., Zhou T., Link prediction in weighted networks: The role of weak ties, Europhysics Letters, 89, 1, (2010)

[8]

Liu H., Zheng H., Et al., Hidden link prediction based on node centrality and weak ties, Europhysics Letters, 101, 1, (2013)

[9]

Zhang J., Jiang Y., A link prediction algorithm based on node similarity, China Science Paper, 8, 7, pp. 660-662, (2013)

[10]

Salton G., Mcgill M.J., Introduction to Modern Information Retrieval, (1983)

← 1 2 →