Link Prediction via Matrix Factorization

  • Aditya Krishna Menon
  • Charles Elkan
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6912)


We propose to solve the link prediction problem in graphs using a supervised matrix factorization approach. The model learns latent features from the topological structure of a (possibly directed) graph, and is shown to make better predictions than popular unsupervised scores. We show how these latent features may be combined with optional explicit features for nodes or edges, which yields better performance than using either type of feature exclusively. Finally, we propose a novel approach to address the class imbalance problem which is common in link prediction by directly optimizing for a ranking loss. Our model is optimized with stochastic gradient descent and scales to large graphs. Results on several datasets show the efficacy of our approach.


Link prediction matrix factorization side information ranking loss 


  1. 1.
    Adamic, L.A., Adar, E.: Friends and neighbors on the web. Social Networks 25(3), 211–230 (2003)CrossRefGoogle Scholar
  2. 2.
    Agarwal, D., Chen, B.-C.: Regression-based latent factor models. In: KDD 2009, pp. 19–28. ACM, New York (2009)Google Scholar
  3. 3.
    Airoldi, E., Blei, D.M., Fienberg, S.E., Xing, E.P.: Mixed membership stochastic blockmodels. In: NIPS, pp. 33–40 (2008)Google Scholar
  4. 4.
    Batagelj, V., Ferligoj, A., Doreian, P.: Generalized blockmodeling. Informatica (Slovenia) 23(4) (1999)Google Scholar
  5. 5.
    Beck, N., King, G., Zeng, L.: Improving quantitative studies of international conflict: A conjecture. American Political Science Review 94(1), 21–36 (2000)CrossRefGoogle Scholar
  6. 6.
    Chawla, N.V., Japkowicz, N., Kotcz, A.: Editorial: special issue on learning from imbalanced data sets. SIGKDD Explor. Newsl. 6, 1–6 (2004)CrossRefGoogle Scholar
  7. 7.
    Chen, H., Li, X., Huang, Z.: Link prediction approach to collaborative filtering. In: Joint Conference on Digital Libraries, vol. 7, pp. 141–142 (2005)Google Scholar
  8. 8.
    Chu, W., Park, S.-T.: Personalized recommendation on dynamic content using predictive bilinear models. In: WWW 2009, pp. 691–700. ACM, New York (2009)Google Scholar
  9. 9.
    Doppa, J.R., Yu, J., Tadepalli, P., Getoor, L.: Learning algorithms for link prediction based on chance constraints. In: Balcázar, J.L., Bonchi, F., Gionis, A., Sebag, M. (eds.) ECML PKDD 2010. LNCS, vol. 6321, pp. 344–360. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  10. 10.
    Dunlavy, D.M., Kolda, T.G., Acar, E.: Temporal link prediction using matrix and tensor factorizations. ACM Transactions on Knowledge Discovery from Data (in Press, 2011)Google Scholar
  11. 11.
    Ruben Gabriel, K.: Generalized bilinear regression. Biometrika 85, 689–700 (1998)MathSciNetCrossRefMATHGoogle Scholar
  12. 12.
    Gantner, Z., Drumond, L., Freudenthaler, C., Rendle, S., Schmidt-Thieme, L.: Learning attribute-to-feature mappings for cold-start recommendations. In: ICDM, pp. 176–185 (2010)Google Scholar
  13. 13.
    Ghosn, F., Palmer, G., Bremer, S.: The MID3 data set, 1993-2001: Procedures, coding rules, and description. Conflict Management and Peace Science 21, 133–154 (2004)CrossRefGoogle Scholar
  14. 14.
    Hasan, M.A., Chaoji, V., Salem, S., Zaki, M.: Link prediction using supervised learning. In: SDM Workshop on Link Analysis, Counterterrorism and Security (2006)Google Scholar
  15. 15.
    Hoff, P.: Modeling homophily and stochastic equivalence in symmetric relational data. In: NIPS (2007)Google Scholar
  16. 16.
    Hoff, P.D.: Bilinear mixed effects models for dyadic data. Journal of the American Statistical Association 32, 100–286 (2003)Google Scholar
  17. 17.
    Hofmann, T., Puzicha, J., Jordan, M.I.: Learning from dyadic data. In: NIPS II, pp. 466–472. MIT Press, Cambridge (1999)Google Scholar
  18. 18.
    Joachims, T.: Optimizing search engines using clickthrough data. In: KDD 2002, pp. 133–142. ACM, New York (2002)Google Scholar
  19. 19.
    Kashima, H., Kato, T., Yamanishi, Y., Sugiyama, M., Tsuda, K.: Link propagation: A fast semi-supervised learning algorithm for link prediction. In: SDM, pp. 1099–1110 (2009)Google Scholar
  20. 20.
    Koren, Y., Bell, R., Volinsky, C.: Matrix factorization techniques for recommender systems. Computer 42, 30–37 (2009)CrossRefGoogle Scholar
  21. 21.
    Lichtenwalter, R., Lussier, J.T., Chawla, N.V.: New perspectives and methods in link prediction. In: KDD, pp. 243–252 (2010)Google Scholar
  22. 22.
    Lu, L., Zhou, T.: Link prediction in complex networks: A survey (2010),
  23. 23.
    Menon, A.K., Elkan, C.: A log-linear model with latent features for dyadic prediction. In: ICDM (2010)Google Scholar
  24. 24.
    Miller, K., Griffiths, T., Jordan, M.: Nonparametric latent feature models for link prediction. In: NIPS, vol. 22, pp. 1276–1284 (2009)Google Scholar
  25. 25.
    Mørup, M., Schmidt, M.N., Hansen, L.K.: Infinite multiple membership relational modeling for complex networks. In: NIPS Workshop on Networks Across Disciplines in Theory and Application (2010)Google Scholar
  26. 26.
    Raymond, R., Kashima, H.: Fast and scalable algorithms for semi-supervised link prediction on static and dynamic graphs. In: Balcázar, J.L., Bonchi, F., Gionis, A., Sebag, M. (eds.) ECML PKDD 2010. LNCS, vol. 6323, pp. 131–147. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  27. 27.
    Rendle, S., Freudenthaler, C., Gantner, Z., Lars, S.-T.: BPR: Bayesian personalized ranking from implicit feedback. In: UAI 2009, pp. 452–461. AUAI Press, Arlington (2009)Google Scholar
  28. 28.
    Roweis, S.: NIPS dataset (2002),
  29. 29.
    Schein, A.I., Popescul, A., Ungar, L.H., Pennock, D.M.: Methods and metrics for cold-start recommendations. In: SIGIR 2002, pp. 253–260. ACM, New York (2002)Google Scholar
  30. 30.
    Sculley, D.: Large scale learning to rank. In: NIPS Workshop on Advances in Ranking (2009)Google Scholar
  31. 31.
    Tsuda, K., Noble, W.S.: Learning kernels from biological networks by maximizing entropy. Bioinformatics 20, 326–333 (2004)CrossRefGoogle Scholar
  32. 32.
    Vert, J.-P., Jacob, L.: Machine learning for in silico virtual screening and chemical genomics: New strategies. Combinatorial Chemistry & High Throughput Screening 11(8), 677–685 (2008)CrossRefGoogle Scholar
  33. 33.
    Wang, C., Satuluri, V., Parthasarathy, S.: Local probabilistic models for link prediction. In: ICDM, pp. 322–331 (2007)Google Scholar
  34. 34.
    Ward, M.D., Siverson, R.M., Cao, X.: Disputes, democracies, and dependencies: A reexamination of the Kantian peace. American Journal of Political Science 51(3), 583–601 (2007)CrossRefGoogle Scholar
  35. 35.
    Watts, D.J., Strogatz, S.H.: Collective dynamics of “small-world” networks. Nature 393(6684), 440–442 (1998)CrossRefGoogle Scholar
  36. 36.
    Yamanishi, Y., Vert, J.-P., Kanehisa, M.: Supervised enzyme network inference from the integration of genomic data and chemical information. In: ISMB (Supplement of Bioinformatics), pp. 468–477 (2005)Google Scholar
  37. 37.
    Yang, S.H., Long, B., Smola, A., Sadagopan, N., Zheng, Z., Zha, H.: Like like alike – joint friendship and interest propagation in social networks. In: WWW (2011)Google Scholar
  38. 38.
    Zhu, S., Yu, K., Chi, Y., Gong, Y.: Combining content and link for classification using matrix factorization. In: SIGIR 2007, pp. 487–494. ACM, New York (2007)Google Scholar
  39. 39.
    Zhu, X., Ghahramani, Z.: Learning from labeled and unlabeled data with label propagation. Technical report, CMU (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Aditya Krishna Menon
    • 1
  • Charles Elkan
    • 1
  1. 1.University of CaliforniaSan Diego La JollaUSA

Personalised recommendations