We propose a new formulation called hyperedge expansion (HE) for hypergraph learning. The HE expansion transforms the hypergraph into a directed graph on the hyperedge level. Compared to the existing works (e.g. star expansion or normalized hypergraph cut), the learning results with HE expansion would be less sensitive to the vertex distribution among clusters, especially in the case that cluster sizes are unbalanced. Because of the special structure of the auxiliary directed graph, the linear eigenvalue problem of the Laplacian can be transformed into a quadratic eigenvalue problem, which has some special properties suitable for semi-supervised learning and clustering problems. We show in the experiments that the new algorithms based on the HE expansion achieves statistically significant gains in classification performance and good scalability for the co-occurrence data.


Left Eigenvector Label Vertex Class Score Quadratic Eigenvalue Problem Vertex Expansion 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Chung, F.: The Laplacian of a hypergraph. Expanding graphs (DIMACS series), pp. 21–36 (1993)Google Scholar
  2. 2.
    Storm, C.: The zeta function of a hypergraph. The Electronic Journal of Combinatorics 13(R84) (2006)Google Scholar
  3. 3.
    Balof, B., Storm, C.: Constructing isospectral non-isomorphic digraphs from hypergraphs. Journal of Graph Theory 63(3), 231–242 (2010)MathSciNetzbMATHCrossRefGoogle Scholar
  4. 4.
    Agarwal, S., Branson, K., Belongie, S.: Higher order learning with graphs. In: Proceedings of the 23rd ICML (2006)Google Scholar
  5. 5.
    Zhou, D., Huang, J., Scholkopf, B.: Learning with hypergraphs: Clustering, classification, and embedding. In: Advances in Neural Information Processing Systems (2007)Google Scholar
  6. 6.
    Karypis, G., Aggarwal, R., Kumar, V., Shekhar, S.: Multilevel hypergraph partitioning: application in VLSI domain. In: Proceedings of the 34th Annual Design Automation Conference (1997)Google Scholar
  7. 7.
    Shashua, A., Zass, R., Hazan, T.: Multi-way Clustering Using Super-Symmetric Non-negative Tensor Factorization. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part IV. LNCS, vol. 3954, pp. 595–608. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  8. 8.
    Bulò, S., Pelillo, M.: A game-theoretic approach to hypergraph clustering. In: Advances in Neural Information Processing Systems (2009)Google Scholar
  9. 9.
    Ladicky, L., Russell, C., Kohli, P., Torr, P.H.S.: Graph Cut Based Inference with Co-occurrence Statistics. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 239–253. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  10. 10.
    Lawler, E.: Cutsets and partitions of hypergraphs. Networks 3(3), 275–285 (1973)MathSciNetzbMATHCrossRefGoogle Scholar
  11. 11.
    Fukunaga, T.: Computing Minimum Multiway Cuts in Hypergraphs from Hypertree Packings. In: Eisenbrand, F., Shepherd, F.B. (eds.) IPCO 2010. LNCS, vol. 6080, pp. 15–28. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  12. 12.
    Acid, S., Campos, L.: An algorithm for finding minimum d-separating sets in belief networks. In: Proceedings of the 12th UAI (1996)Google Scholar
  13. 13.
    Wu, C.: On Rayleigh-Ritz ratios of a generalized Laplacian matrix of directed graphs. Linear Algebra and Its Applications 402, 207–227 (2005)MathSciNetzbMATHCrossRefGoogle Scholar
  14. 14.
    Chung, F.: Laplacians and the Cheeger inequality for directed graphs. Annals of Combinatorics 9(1), 1–19 (2005)MathSciNetzbMATHCrossRefGoogle Scholar
  15. 15.
    Zhou, D., Huang, J., Schölkopf, B.: Learning from labeled and unlabeled data on a directed graph. In: Proceedings of the 22nd ICML (2005)Google Scholar
  16. 16.
    Horn, R., Johnson, C.: Topics in Matrix Analysis. Cambridge University Press (1991)Google Scholar
  17. 17.
    Guo, C., Lancaster, P.: Algorithms for hyperbolic quadratic eigenvalue problems. Mathematics of Computation, 1777–1791 (2005)Google Scholar
  18. 18.
    Sun, L., Ji, S., Ye, J.: Hypergraph spectral learning for multi-label classification. In: Proceeding of the 14th ACM SIGKDD (2008)Google Scholar
  19. 19.
    Von Luxburg, U.: A tutorial on spectral clustering. Statistics and Computing 17(4), 395–416 (2007)MathSciNetCrossRefGoogle Scholar
  20. 20.
    Lin, F., Cohen, W.: Semi-supervised classification of network data using very few labels. In: International Conference on Advances in Social Networks Analysis and Mining, pp. 192–199 (2010)Google Scholar
  21. 21.
    Strehl, A., Ghosh, J.: Cluster ensembles – a knowledge reuse framework for combining multiple partitions. Journal of Machine Learning Research 3, 583–617 (2003)MathSciNetzbMATHGoogle Scholar
  22. 22.
    Azran, A.: The rendezvous algorithm: Multiclass semi-supervised learning with markov random walks. In: Proceedings of the 24th ICML (2007)Google Scholar
  23. 23.
    Kulis, B., Basu, S., Dhillon, I., Mooney, R.: Semi-supervised graph clustering: a kernel approach. In: Proceedings of the 22nd ICML (2005)Google Scholar
  24. 24.
    Liu, W., He, J., Chang, S.: Large graph construction for scalable semi-supervised learning. In: Proceedings of the 27th ICML (2010)Google Scholar
  25. 25.

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Li Pu
    • 1
  • Boi Faltings
    • 1
  1. 1.Artificial Intelligence LaboratoryÉcole Polytechnique Fédérale de LausanneLausanneSwitzerland

Personalised recommendations