Ray Liere, Prasad Tadepalli
In many real-world domains, supervised learning requires a large number of training examples. In this paper, we describe an active learning method that uses a committee of learners to reduce the number of training examples required for learning. Our approach is similar to the Query by Committee framework, where disagreement among the committee members on the predicted label for the input part of the example is used to signal the need for knowing the actual value of the label. Our experiments are conducted in the text categorization domain, which is characterized by a large number of features, many of which are irrelevant. We report here on experiments using a committee of Winnow-based learners and demonstrate that this approach can reduce the number of labeled training examples required over that used by a single Winnow learner by l-2 orders of magnitude.