Balancing Learning and Overfitting in Genetic Programming with Interleaved Sampling of Training Data
Generalization is the ability of a model to perform well on cases not seen during the training phase. In Genetic Programming generalization has recently been recognized as an important open issue, and increased efforts are being made towards evolving models that do not overfit. In this work we expand on recent developments that showed that using a small and frequently changing subset of the training data is effective in reducing overfitting and improving generalization. Particularly, we build upon the idea of randomly choosing a single training instance at each generation and balance it with periodically using all training data. The motivation for this approach is based on trying to keep overfitting low (represented by using a single training instance) and still presenting enough information so that a general pattern can be found (represented by using all training data). We propose two approaches called interleaved sampling and random interleaved sampling that respectively represent doing this balancing in a deterministic or a probabilistic way. Experiments are conducted on three high-dimensional real-life datasets on the pharmacokinetics domain. Results show that most of the variants of the proposed approaches are able to consistently improve generalization and reduce overfitting when compared to standard Genetic Programming. The best variants are even able of such improvements on a dataset where a recent and representative state-of-the-art method could not. Furthermore, the resulting models are short and hence easier to interpret, an important achievement from the applications’ point of view.
KeywordsGenetic Programming Overfitting Generalization Pharmacokinetics Drug Discovery
Unable to display preview. Download preview PDF.
- 3.Gonçalves, I., Silva, S.: Experiments on controlling overfitting in genetic programming. In: Proceedings of the 15th Portuguese Conference on Artificial Intelligence: Progress in Artificial Intelligence, EPIA 2011 (2011)Google Scholar
- 6.Kola, I., Landis, J.: Can the pharmaceutical industry reduce attrition rates? Nat. Rev. Drug Discov. 3(8), 711–716 (2004)Google Scholar
- 7.Koza, J.R.: Genetic Programming: On the Programming of Computers by Means of Natural Selection (Complex Adaptive Systems), 1st edn. The MIT Press (1992)Google Scholar
- 10.Langdon, W.B.: Minimising testing in genetic programming. Tech. Rep. RN/11/10, Computer Science, University College London, Gower Street, London WC1E 6BT, UK (2011)Google Scholar
- 11.Liu, Y., Khoshgoftaar, T.: Reducing overfitting in genetic programming models for software quality classification. In: Proceedings of the Eighth IEEE International Conference on High Assurance Systems Engineering, HASE 2004, pp. 56–65. IEEE Computer Society, Washington, DC (2004)CrossRefGoogle Scholar
- 13.Poli, R., Langdon, W.B., McPhee, N.F.: A field guide to genetic programming (2008)Google Scholar
- 15.Silva, S., Vanneschi, L.: Bloat free genetic programming: Application to human oral bioavailability prediction. International Journal of Data Mining and Bioinformatics 6(6), 585–601 (2012)Google Scholar