Y: Exploiting Ontology Structures and Unlabeled Data for Learning

We present and analyze a theoretical model designed to understand and explain the ef-fectiveness of ontologies for learning multi-ple 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. 1