A mixed discrete-continuous attribute list representation for large scale classification domains

Abstract

Datasets with a large number of attributes are a difficult challenge for evolutionary learning techniques. The recently proposed attribute list rule representation has shown to be able to significantly improve the overall performance (e.g. run-time, accuracy, rule set size) of the BioHEL Iterative Evolutionary Rule Learning system. In this paper we, first, extend the attribute list rule representation so it can handle not only continuous domains, but also datasets with a very large number of mixed discrete-continuous attributes. Secondly, we benchmark the new representation with a diverse set of large-scale datasets and, third, we compare the new algorithms with several well-known machine learning methods. The experimental results we describe in the paper show that the new representation is equal or better than the state of-the-art in evolutionary rule representations both in terms of the accuracy obtained with the benchmark datasets used, as well as in terms of the computational time requirements needed to achieve these improved accuracies. The new attribute list representation puts BioHEL on an equal footing with other well-established machine learning techniques in terms of accuracy. In the paper, we also analyse and discuss the current weaknesses behind the current representation and indicate potential avenues for correcting them.