Advertisement

Automatic Control and Computer Sciences

, Volume 52, Issue 5, pp 412–420 | Cite as

A Recursive Bayesian Approach for the Link Prediction Problem

  • Cheng JiangEmail author
  • Jie Sui
  • Hua Yu
Article
  • 22 Downloads

Abstract

Recently, link prediction techniques have been increasingly adopted to discover link patterns in various domains. On challenging problem is to improve the performance continually. In this paper, we propose a recursive prediction mechanism to addresses the link prediction problem. A posterior is calculated based on observed data, and then we estimate the state of the graph and use the posterior as the prior distribution for the next stage. With the increasing of iterations, the proposed approach incorporates more and more topological structure information and node attributes data. Experimental results with real-world networks have shown that the proposed solution performs better in terms of well-known metrics as compared to the existing approaches. This novel approach has already been integrated into an expert system and provides auxiliary support for decision-makers.

Keywords:

recursive Bayesian link prediction expert system statistical inference 

Notes

ACKOWLEDGMENTS

This work is supported by National Natural Science Foundation of China with grant no. 61572459.

REFERENCES

  1. 1.
    Wang, D., Pedreschi, C.M., and Song, F., Giannotti and A.L. Barabási, Human mobility, social ties, and link prediction, Knowledge Discovery and Data Mining (KDD), Proceedings of the 17th ACM SIGKDD International Conference On, 2011, pp. 1100–1108.Google Scholar
  2. 2.
    Pujari, P. and Kanawati, R., Tag recommendation by link prediction based on supervised machine learning, Weblogs and Social Media (AAAI), Proceedings of the 6th International AAAI Conference On, 2012, pp. 547–550.Google Scholar
  3. 3.
    Xie, F., Chen, Z., Shang, J.X., Feng, X.P., and Li, J., A link prediction approach for item recommendation with complex number, Knowl.-Based Syst., 2015, vol. 81, pp. 148–158.CrossRefGoogle Scholar
  4. 4.
    Kumar, P.R. and Singh, A.K., Web structure mining: Exploring hyperlinks and algorithm for information retrieval, Am. J. Appl. Sci., 2010, vol. 7, pp. 840–845.CrossRefGoogle Scholar
  5. 5.
    Jansen, R., Yu, H.Y., Greenbaum, D., Kluger, Y., Krogan, N.J., Chung, S., Emili, A., Snyder, M., Greenblatt, J.F., and Gerstein, M., A Bayesian networks approach for predicting protein-protein interactions from genomic data, Science, 2003, vol. 302, pp. 449–453.CrossRefGoogle Scholar
  6. 6.
    Rhodes, C.J. and Keefe, E.M.J., Social network topology: A Bayesian approach, J. Oper. Res. Soc., 2007, vol. 58, pp. 1605–1611.CrossRefGoogle Scholar
  7. 7.
    Lü, L.Y. and Zhou, T., Link prediction in complex networks: A survey, Phys. A: Stat. Mech. Its Appl., 2011, vol. 390, pp. 1150–1170.CrossRefGoogle Scholar
  8. 8.
    Newman, M.E., Clustering and preferential attachment in growing networks, Phys. Rev., 2001, vol. 64, 025102.Google Scholar
  9. 9.
    Katz, L., A new status index derived from sociometric analysis, Psychometrika, 1953, vol. 18, pp. 39–43.CrossRefzbMATHGoogle Scholar
  10. 10.
    Adamic, L.A. and Adar, E., Friends and neighbors on the web, Soc. Network, 2003, vol. 25, pp. 211–230.CrossRefGoogle Scholar
  11. 11.
    Barabási, A.L. and Albert, R., Emergence of scaling in random networks, Science, 1999, vol. 286, pp. 509–512.MathSciNetCrossRefzbMATHGoogle Scholar
  12. 12.
    Li, F.H., He, J., Huang, G.Y., Zhang, Y.C., Shi, Y., and Zhou, R., Node-coupling clustering approaches for link prediction, Knowl.-Based Syst., 2015, vol. 89, pp. 669–680.CrossRefGoogle Scholar
  13. 13.
    Jamakovic, A. and Uhlig, S., On the relationships between topological measures in real-world networks, Networks Heterog. Media, 2008, vol. 3, pp. 345–359.MathSciNetCrossRefzbMATHGoogle Scholar
  14. 14.
    Xie, Z., Dong, E.M., Li, J.P., Kong, D.X., and Wu, N., Potential links by neighbor communities, Phys. A: Stat. Mech. Its Appl., 2014, vol. 406, pp. 244–252.CrossRefzbMATHGoogle Scholar
  15. 15.
    Yu, Z., Feng, L., Bin, X., Kening, G., and Ge, Y., Using non-topological node attribute to improve results of link prediction in social networks, Proceedings of the 2012 Ninth Web Information Systems and Applications Conference (WISA), 2012.Google Scholar
  16. 16.
    Backstrom, L. and Leskovec, J., Supervised random walks: Predicting and recommending links in social networks, Web Search and Data Mining (WSDM), Proceedings of the Fourth ACM International Conference On, 2011, pp. 635–644.Google Scholar
  17. 17.
    Soares, P.R.S. and Prudêncio, R.B.C., Time series based link prediction, Neural Networks (IJCNN), The 2012 International Joint Conference On, 2012, pp. 1–7.Google Scholar
  18. 18.
    Zamba, K.D., Tsiamyrtzis, P., and Hawkins, D.M., A three-state recursive sequential Bayesian algorithm for biosurveillance, Inf. J. Comput., 2013, vol. 21, pp. 286–303.zbMATHGoogle Scholar
  19. 19.
    Huang, Z. and Lin, D.K.J., The time-series link prediction problem with application in communication surveillance, Inf. J. Comput., 2008, vol. 21, pp. 286–303.CrossRefGoogle Scholar
  20. 20.
    Han, M. and Ding, Y.Y., Synthesized expected Bayesian method of parametric estimate, J. Syst. Sci. Syst. Eng., 2004, vol. 13, pp. 98–111.CrossRefGoogle Scholar
  21. 21.
    Oravecz, Z., Vandekerckhove, J., and Huentelman, M., Sequential Bayesian updating for big data, in Big Data in Cognitive Science: From Methods to Insights, University of California, 2016.Google Scholar
  22. 22.
    John Jay and ARITS Transnational Terrorism Database (JJATT). http://doitapps.jjay.cuny.edu/jjatt. Accessed May 14th, 2017.Google Scholar

Copyright information

© Allerton Press, Inc. 2018

Authors and Affiliations

  1. 1.Information School, Capital University of Economics and BusinessBeijingChina
  2. 2.School of Engineering Science, University of Chinese Academy of SciencesBeijingChina

Personalised recommendations