Machine Learning

, Volume 93, Issue 1, pp 141–161

Pairwise meta-rules for better meta-learning-based algorithm ranking

Article

DOI: 10.1007/s10994-013-5387-y

Cite this article as:
Sun, Q. & Pfahringer, B. Mach Learn (2013) 93: 141. doi:10.1007/s10994-013-5387-y

Abstract

In this paper, we present a novel meta-feature generation method in the context of meta-learning, which is based on rules that compare the performance of individual base learners in a one-against-one manner. In addition to these new meta-features, we also introduce a new meta-learner called Approximate Ranking Tree Forests (ART Forests) that performs very competitively when compared with several state-of-the-art meta-learners. Our experimental results are based on a large collection of datasets and show that the proposed new techniques can improve the overall performance of meta-learning for algorithm ranking significantly. A key point in our approach is that each performance figure of any base learner for any specific dataset is generated by optimising the parameters of the base learner separately for each dataset.

Keywords

Meta-learning Algorithm ranking Ranking trees Ensemble learning 

Copyright information

© The Author(s) 2013

Authors and Affiliations

  1. 1.Department of Computer ScienceThe University of WaikatoHamiltonNew Zealand

Personalised recommendations