Compact Dual Ensembles for Active Learning
Generic ensemble methods can achieve excellent learning performance, but are not good candidates for active learning because of their different design purposes. We investigate how to use diversity of the member classifiers of an ensemble for efficient active learning. We empirically show, using benchmark data sets, that (1) to achieve a good (stable) ensemble, the number of classifiers needed in the ensemble varies for different data sets; (2) feature selection can be applied for classifier selection from ensembles to construct compact ensembles with high performance. Benchmark data sets and a real-world application are used to demonstrate the effectiveness of the proposed approach.