A Neural Network Approach to Similarity Learning

  • Stefano Melacci
  • Lorenzo Sarti
  • Marco Maggini
  • Monica Bianchini
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5064)

Abstract

This paper presents a novel neural network model, called similarity neural network (SNN), designed to learn similarity measures for pairs of patterns. The model guarantees to compute a non negative and symmetric measure, and shows good generalization capabilities even if a very small set of supervised examples is used for training. Preliminary experiments, carried out on some UCI datasets, are presented, showing promising results.

Keywords

Similarity Measure Mahalanobis Distance Neural Network Approach Pairwise Constraint Sigmoidal Activation Function 
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.
Download to read the full conference paper text

References

  1. 1.
    Tversky, A.: Features of Similarity. Psychological Review 84(4), 327–352 (1977)CrossRefGoogle Scholar
  2. 2.
    Xing, E., Ng, A., Jordan, M., Russell, S.: Distance metric learning, with application to clustering with side-information. Advances in Neural Information Processing Systems 15, 505–512 (2003)Google Scholar
  3. 3.
    De Bie, T., Momma, M., Cristianini, N.: Efficiently learning the metric using side-information. In: Proc. Int. Conf. on Algorithmic Learning Theory, pp. 175–189 (2003)Google Scholar
  4. 4.
    Bilenko, M., Basu, S., Mooney, R.: Integrating constraints and metric learning in semi-supervised clustering. In: Proc. Int. Conf. on Machine Learning, pp. 81–88 (2004)Google Scholar
  5. 5.
    Basu, S., Bilenko, M., Mooney, R.: A probabilistic framework for semi-supervised clustering. In: Proc. Int. Conf. on Knowledge Discovery and Data Mining, pp. 59–68 (2004)Google Scholar
  6. 6.
    Bar-Hillel, A., Hertz, T., Shental, N., Weinshall, D.: Learning a Mahalanobis Metric from Equivalence Constraints. J. Machine Learning Research 6, 937–965 (2005)MathSciNetGoogle Scholar
  7. 7.
    Tsang, I., Kwok, J.: Distance metric learning with kernels. In: Proc. Int. Conf. on Artificial Neural Networks, pp. 126–129 (2003)Google Scholar
  8. 8.
    Bianchini, M., Gori, M., Scarselli, F.: Processing directed acyclic graphs with recursive neural networks. IEEE Trans. on Neural Networks 12(6), 1464–1470 (2001)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Stefano Melacci
    • 1
  • Lorenzo Sarti
    • 1
  • Marco Maggini
    • 1
  • Monica Bianchini
    • 1
  1. 1.DIIUniversità degli Studi di SienaSienaItaly

Personalised recommendations