Developing an Active Learning algorithm for learning Bayesian classifiers under the Multiple Instance Learning scenario

Abstract

In the Multiple Instance Learning scenario, the training data consists of instances grouped into bags, and each bag is labelled with whether it is positive, i.e. contains at least one positive instance. First, Active Learning, in which additional labels can be iteratively requested, has the potential to allow more accurate classi?ers to be learned with less labels. Active Learning has been applied to the Multiple Instance Learning under two settings: when bag labels of unlabelled bags can be requested, and when instance labels within bags known to be positive can be requested. Second, Bayesian Active learning methods have the potential to learn accurate classi?ers with few labels, because they explicitly track the classi?er uncertainty and can thus address its knowledge gaps. Yet, there does not exist any Bayesian Active Learning method for the Multiple Instance Learning Scenario. In this work, we develop the ?rst such method. We develop a Bayesian classi?er for the Multiple Instance Learning scenario, show how it can be ef?ciently used for Bayesian Active Learning, and perform experiments assessing its performance. While its performance exceeds that when no Active Learning is used, it is sometimes better, sometimes worse than the naive baseline of uncertainty sampling, depending on the situation. This suggests future work: building more customizable Bayesian Active Learning methods for the Multiple Instance Scenario, customizable to whether bag or instance label accuracy is targeted, and the labeling budget.

Related Papers

• → On the relation between multi-instance learning and semi-supervised learning(2007)164 cited
• → A new semi-supervised support vector machine learning algorithm based on active learning(2010)19 cited
• → Combining active learning and semi-supervised for improving learning performance(2011)3 cited
• → Efficient Learning from Few Labeled Examples(2009)
• Optimal Active Learning: experimental factors and membership query learning(2010)