Abstract

Co-training is a well known semi-supervised learning algorithm, in which two classifiers are trained on two different views (feature sets): the initially small training set is iteratively updated with unlabelled samples classified with high confidence by one of the two classifiers. In this paper we address an issue that has been overlooked so far in the literature, namely, how co-training performance is affected by the size of the initial training set, as it decreases to the minimum value below which a given learning algorithm can not be applied anymore. In this paper we address this issue empirically, testing the algorithm on 24 real datasets artificially splitted in two views, using two different base classifiers. Our results show that a very small training set, even made up of one only labelled sample per class, does not adversely affect co-training performance.

Keywords

Semi-supervised learning Co-training Small sample size 

References

  1. 1.
    Blum, A., Mitchell, T.: Combining labeled and unlabeled data with co-training. In: Proceedings 11th Annual Conference on Computational Learning Theory, pp. 92–100. ACM (1998)Google Scholar
  2. 2.
    Balcan, M.F., Blum, A., Yang, K., Saul, L.K.: Co-Training and Expansion: Towards Bridging Theory and Practice. In: Weiss, Y., Bottou, L. (eds.) Advances in Neural Information Processing Systems 17, pp. 89–96. MIT Press (2005)Google Scholar
  3. 3.
    Christoudias, C.M., Urtasun, R., Kapoorz, A., Darrell, T.: Co-training with noisy perceptual observations. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2844–2851 (2009)Google Scholar
  4. 4.
    Didaci, L., Roli, F.: A Bayesian Analysis of Co-Training Algorithm with Insufficient Views. In: Proc. 11th International Conference on Information Science, Signal Processing and their Applications, pp. 1141–1145. IEEE (2012)Google Scholar
  5. 5.
    Du, J., Ling, C.X., Zhou, Z.-H.: When Does Co-Training Work in Real Data? IEEE Transactions on Knowledge and Data Engineering 23(35), 788–799 (2011)CrossRefGoogle Scholar
  6. 6.
    Zhou, Z.-H., Zhan, D.-C., Yang, Q.: Semi-Supervised Learning with Very Few Labeled Training Examples. In: Proc. AAAI, pp. 675–680 (2007)Google Scholar
  7. 7.
    Frank, A., Asuncion, A.: UCI Machine Learning Repository. University of California, School of Information and Computer Science, Irvine, CA (2010), http://archive.ics.uci.edu/ml

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Luca Didaci
    • 1
  • Giorgio Fumera
    • 1
  • Fabio Roli
    • 1
  1. 1.Department of Electrical and Electronic EngineeringUniversity of CagliariCagliariItaly

Personalised recommendations