Abstract
In many real problems that ultimately require data classification, not all the class labels are readily available. This concerns the field of semi-supervised learning, in which missing class labels must be inferred from the available ones as well as from the natural cluster structure of the data. This structure can sometimes be quite convoluted. Previous research has shown the advantage, for these cases, of using the geodesic metric in clustering models of the manifold learning family to reveal the underlying true data structure. In this brief paper, we present a novel semi-supervised approach, namely Semi-Supervised Geo-GTM (SS-Geo-GTM). This is an extension of Geo-GTM, a variation on the Generative Topographic Mapping (GTM) manifold learning model for data clustering and visualization that resorts to the geodesic metric. SS-Geo-GTM uses a proximity graph built from Geo-GTM manifold as the basis for a label propagation algorithm that infers missing class labels. Its performance is compared to those of a semi-supervised version of the standard GTM and of the alternative Laplacian Eigenmaps method.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Chapelle, O., Schölkopf, B., Zien, A. (eds.): Semi-Supervised Learning. MIT Press, Cambridge (2006)
Herrmann, L., Ultsch, A.: Label propagation for semi-supervised learning in self-organizing maps. In: Proceedings of the 6th WSOM 2007 (2007)
Ultsch, A.: Maps for the visualization of high-dimensional data spaces. In: Proceedings of WSOM 2003, 225–230 (2003)
Cruz-Barbosa, R., Vellido, A.: Unfolding the manifold in Generative Topographic Mapping. In: Corchado, E., Abraham, A., Pedrycz, W. (eds.) HAIS 2008. LNCS (LNAI), vol. 5271, pp. 392–399. Springer, Heidelberg (2008)
Bishop, C.M., Svensén, M., Williams, C.K.I.: The Generative Topographic Mapping. Neural Computation 10(1), 215–234 (1998)
Belkin, M., Niyogi, P.: Using manifold structure for partially labelled classification. In: Procs. of NIPS, vol. 15. MIT Press, Cambridge (2003)
Tenenbaum, J.B., de Silva, V., Langford, J.C.: A global geometric framework for nonlinear dimensionality reduction. Science 290, 2319–2323 (2000)
Lee, J.A., Lendasse, A., Verleysen, M.: Curvilinear distance analysis versus isomap. In: Procs. of the ESANN, pp. 185–192 (2002)
Bernstein, M., de Silva, V., Langford, J., Tenenbaum, J.: Graph approximations to geodesics on embedded manifolds. Technical report, Stanford U., CA (2000)
Dijkstra, E.W.: A note on two problems in connection with graphs. Numerische Mathematik 1, 269–271 (1959)
Archambeau, C., Verleysen, M.: Manifold constrained finite gaussian mixtures. In: Cabestany, J., Prieto, A.G., Sandoval, F. (eds.) IWANN 2005. LNCS, vol. 3512, pp. 820–828. Springer, Heidelberg (2005)
Zhu, X., Ghahramani, Z.: Learning from labeled and unlabeled data with label propagation. Technical report, CMU-CALD-02-107, Carnegie Mellon University (2002)
Cruz-Barbosa, R., Vellido, A.: Geodesic Generative Topographic Mapping. In: Geffner, H., Prada, R., Machado Alexandre, I., David, N. (eds.) IBERAMIA 2008. LNCS (LNAI), vol. 5290, pp. 113–122. Springer, Heidelberg (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cruz-Barbosa, R., Vellido, A. (2009). Comparative Evaluation of Semi-supervised Geodesic GTM. In: Corchado, E., Wu, X., Oja, E., Herrero, Á., Baruque, B. (eds) Hybrid Artificial Intelligence Systems. HAIS 2009. Lecture Notes in Computer Science(), vol 5572. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-02319-4_41
Download citation
DOI: https://doi.org/10.1007/978-3-642-02319-4_41
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-02318-7
Online ISBN: 978-3-642-02319-4
eBook Packages: Computer ScienceComputer Science (R0)