PAC Generalization Bounds for Co-training

The rule-based bootstrapping introduced by Yarowsky, and its cotraining variant by Blum and Mitchell, have met with considerable empirical success. Earlier work on the theory of co-training has been only loosely related to empirically useful co-training algorithms. Here we give a new PAC-style bound on generalization error which justifies both the use of confidences -- partial rules and partial labeling of the unlabeled data -- and the use of an agreement-based objective function as suggested by Collins and Singer. Our bounds apply to the multiclass case, i.e., where instances are to be assigned one of labels for

• Type: Conference
• Year: 2001
• Where: NIPS
• Authors: Sanjoy Dasgupta, Michael L. Littman, David A. McAllester
• Keywords: Considerable Empirical Success, NIPS 2001, NIPS 2007, Rule-based Bootstrapping, Useful Co-training Algorithms