Exploiting Ontology Structures and Unlabeled Data for Learning

2005-09-01T00:00:00Z (GMT) by Nina Balcan Avrim Blum Yishay Mansour

We present and analyze a theoretical model designed to understand and explain the effectiveness of ontologies for learning multiple related tasks from primarily unlabeled data. We present both information-theoretic results as well as efficient algorithms. We show in this model that an ontology, which specifies the relationships between multiple outputs, in some cases is sufficient to completely learn a classification using a large unlabeled data source