Supervised Learning and Co-training

Co-training under the Conditional Independence Assumption is among the models which demonstrate how radically the need for labeled data can be reduced if a huge amount of unlabeled data is available. In this paper, we explore how much credit for this saving must be assigned solely to the extra-assumptions underlying the Co-training model. To this end, we compute general (almost tight) upper and lower bounds on the sample size needed to achieve the success criterion of PAClearning within the model of Co-training under the Conditional Independence Assumption in a purely supervised setting. The upper bounds lie significantly below the lower bounds for PAC-learning without Cotraining. Thus, Co-training saves labeled data even when not combined with unlabeled data. On the other hand, the saving is much less radical than the known savings in the semi-supervised setting.