Abstract
A crucial factor for successful learning is the finding of more convenient representations for a problem, such that subsequent processing can be delivered to linear or non-linear modeling methods. Similarity functions are a flexible way to express knowledge about a problem and to capture meaningful relations of data in input space. In this paper we use similarity functions to find an alternative data representation which is then reduced by selecting a subset of relevant prototypes, in a supervised way. The idea is tested in a set of modelling problems, characterized by a mixture of data types and different amounts of missing values. The results demonstrate competitive or better performance than traditional methods in terms of prediction error and sparsity of the representation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
For example, by the presence of missing values, by the feature semantics, etc.
- 2.
Such variables are increasingly common, especially when they refer to a time periodicity, such as the month in a year.
- 3.
It is not difficult to check that this is equivalent to the replacement of the missing similarities by the average of the non-missing ones. Therefore, the conjecture is that the missing values, if known, would not change the overall similarity significantly.
- 4.
This property is not used in this work but it is interesting in other contexts, such as optimization.
- 5.
The experiments were run on a HP laptop with 2GB of RAM and an Intel(R) Core(TM)2 Duo CPU T7500 at 2.20GHz.
- 6.
See the caption of Table 1 for a description.
References
Osborne, H., Bridge, D. Models of similarity for case-based reasoning. In: Interdisciplinary Workshop on Similarity and Categorisation, pp. 173–179 (1997)
Tibshirani, R.: Regression Shrinkage and Selection via the lasso. J. R. Stat. Soc. Ser. B. Wiley 58(1), 26788 (1996)
Baeza-Yates, R., Ribeiro, B.: Modern Information Retrieval. ACM Press, New York (1999)
Shawe-Taylor, J., Cristianini, N.: Kernel Methods for Pattern Analysis. Camb. Univ Press, Cambridge (2004)
UCI Machine Learning Repository. http://archive.ics.uci.edu/ml
Pekalska, E.: The Dissimilarity representations in pattern recognition. Concepts, theory and applications. (Ph.D. Thesis) Delft University of Technology (2005)
Duin, R.P.W., Loog, M., Pekalska, E., Tax, D.M.J.: Feature-based dissimilarity space classification. In: Ünay, D., Çataltepe, Z., Aksoy, S. (eds.) ICPR 2010. LNCS, vol. 6388, pp. 46–55. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-17711-8_5
Garain, U.: Prototype reduction using an artificial immune model. Pattern Anal. Appl. 11(3–4), 353–363 (2008)
Gower, J.C.: A general coefficient of similarity and some of its properties. Biometrika 27(4), 857–871 (1971)
Sokal, R.R., Michener, C.D.: Principles of Numerical Taxonomy. W.H. Freeman, San Francisco (1963)
Dixon, J.K.: Pattern recognition with partly missing data. IEEE Trans. Syst. Man Cybernet. 9, 617–621 (1979)
Gower, J.C., Legendre, P.: Metric and Euclidean Properties of Dissimilarity Coefficients. J. Classification 3, 5–48 (1986)
Pavoine, S., Vallet, J., Dufour, A.B., Gachet, S., Daniel, H.: On the challenge of treating various types of variables: application for improving the measurement of functional diversity. Oikos 118(3), 391–402 (2009)
Caputo, B., Sim, K., Furesjo, F., Smola, A.: Appearance-based object recognition using SVMs: which kernel should I use? In: NIPS Workshop on Statistical methods for Computational Experiments in Visual Processing and Computer Vision (2002)
van Buuren, S., Groothuis-Oudshoorn, K.: mice: multivariate imputation by chained equations in R. J. Stat. Softw. 45(3), 1–67 (2011)
Ripley, B.: Pattern Recognition and Neural Networks. Camb. Univ Press, Cambridge (1996)
Ravindra Babu, T., Narasimha Murty, M.: Comparison of genetic algorithm based prototype selection schemes. Pattern Recognit. 34, 523–525 (2001)
Belanche, L.l., Hernández, J.: Similarity networks for heterogeneous data. In: Proceedings of the ESANN: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (2012)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Kuncheva, L., Bezdek, J.: Nearest prototype classification: clustering, genetic algorithms, or random search? IEEE Trans. Syst. Man Cybern. Part C 28(1), 160–164 (1998)
Lipowezky, U.: Selection of the optimal prototype subset for 1-NN classification. Pattern Recognit. Lett. 19, 907–918 (1998)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Belanche, L.A. (2018). Fast Supervised Selection of Prototypes for Metric-Based Learning. In: Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds) Artificial Neural Networks and Machine Learning – ICANN 2018. ICANN 2018. Lecture Notes in Computer Science(), vol 11140. Springer, Cham. https://doi.org/10.1007/978-3-030-01421-6_55
Download citation
DOI: https://doi.org/10.1007/978-3-030-01421-6_55
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-01420-9
Online ISBN: 978-3-030-01421-6
eBook Packages: Computer ScienceComputer Science (R0)