Online Choice of Active Learning Algorithms

Proceedings of the Twentieth International Conference on Machine Learning

Volume

Proceedings of the Twentieth International Conference on Machine Learning

Contents

This paper is concerned with the question of how to online combine an ensemble of active learners so as to expedite the learning progress during a pool-based active learning session. We develop a powerful active learning master algorithm, based a known competitive algorithm for the multi-armed bandit problem and a novel semi-supervised performance evaluation statistic. Taking an ensemble containing two of the best known active learning algorithms and a new algorithm, the resulting new active learning master algorithm is empirically shown to consistently perform almost as well as and sometimes outperform the best algorithm in the ensemble on a range of classification problems.