Improved Link Prediction Using PCA

Main Article Content

. Ankita, Nanhay Singh


Link Prediction is known as a challenging problem in the area of online social media. Earlier, learning model for link prediction task has been proposed by many researchers. But the classification of imbalanced and high dimensional data is an interesting and challenging problem in machine learning due to presence of unbalanced and redundant or correlated data which break down the classification performance. In this paper, we have balanced the data and used Principle Component Analysis (PCA) to reduce the correlated data and improved the performance of link prediction model. Experiment is carried out on social network data set and the use of PCA method has improved the performance in classification of links.

Article Details


  1. Huang, Z, Dajun Zeng, D. A link prediction approach to anomalous email detection. In: IEEE International Conference on Systems, Man and Cybernetics, San Diego, CA, 2006, 1131?1136.
  2. Folino, F. and Pizzuti, C., Link prediction approaches for disease networks. In International Conference on Information Technology in Bio-and Medical Informatics. Springer, Berlin, Heidelberg, 2012, 99-108.
  3. Esslimani, I., Brun, A. and Boyer, A., Densifying a behavioral recommender system by social networks link prediction methods. Social Network Anal. Mining, 1(3)(2011), 159-172.
  4. Chen, H., Li, X. and Huang, Z., Link prediction approach to collaborative filtering. In Proceedings of the 5th ACM/IEEECS Joint Conference on Digital Libraries (JCDL'05), IEEE, 2005, 141-142.
  5. Lu, L., Jin, C.H. and Zhou, T., Similarity index based on local paths for link prediction of complex networks. Phys. Rev. E, 80(4)(2009), 046122.
  6. Liu, W. and L ¨u, L., Link prediction based on local random walk. Europhys. Lett. 89(5)(2010), 58007.
  7. Benchettara, N., Kanawati, R. and Rouveirol, C., Supervised machine learning applied to link prediction in bipartite social networks. In 2010 International Conference on Advances in Social Networks Analysis and Mining. IEEE 2010, 326-330.
  8. Liben-Nowell, David, and Kleinberg, Jon. The Link Prediction Problem for Social Networks. J. Amer. Soc. Inf. Sci. Technol. 58(7)(2007), 1019-1031
  9. Al Hasan, M., Chaoji, V., Salem, S. and Zaki, M., April. Link prediction using supervised learning. In SDM06: workshop on link analysis, counter-terrorism and security, 2006.
  10. De Sa, H.R. and Prudencio, R.B., Supervised link prediction in weighted networks. In The 2011 international joint conference on neural networks, IEEE, 2011, 2281-2288.
  11. Almansoori, W., Gao, S., Jarada, T.N., Elsheikh, A.M., Murshed, A.N., Jida, J., Alhajj, R. and Rokne, J., Link prediction and classification in social networks and its application in healthcare and systems biology. Network Modeling Analysis in Health Informatics and Bioinformatics, 1(1-2)(2012), 27-36.
  12. Liu, Z., Zhang, Q.M., L ¨u, L. and Zhou, T., Link prediction in complex networks: A local nave Bayes model. Europhys. Lett. 96(4)(2011), 48007.
  13. O'Madadhain, J., Hutchins, J. and Smyth, P., Prediction and ranking algorithms for event-based network data. ACM SIGKDD explorations newsletter, 7(2)(2005), 23-30.
  14. Al Hasan, M. and Zaki, M.J., A survey of link prediction in social networks. In Social network data analytics. Springer, Boston, MA. 2011. 243-275.
  15. Kashima, H. and Abe, N., A parameterized probabilistic model of network evolution for supervised link prediction. In Sixth International Conference on Data Mining (ICDM'06). IEEE. 2006, 340-349.
  16. Fawcett, T., An introduction to ROC analysis. Pattern Recognition Letters, 27(8)(2006), 861-874.
  17. Liu, H., Hu, Z., Haddadi, H. and Tian, H., Hidden link prediction based on node centrality and weak ties. Europhys. Lett. 101(1)(2013), 18004.
  18. Freeman, L.C., Centrality in social networks conceptual clarification. Social networks, 1(3)(1978), 215-239.
  19. Sabidussi G., The centrality of a graph, Psychometrika 31(4)(1966), 581-603.
  20. Yao, L., Wang, L., Pan, L. and Yao, K., Link prediction based on common-neighbors for dynamic social network. Proc. Computer Sci. 83(2016), 82-89.