Theoretical Comparisons of Learning from Positive-Negative, Positive-Unlabeled, and Negative-Unlabeled Data

In PU learning, a binary classifier is trained only from positive (P) and unlabeled (U) data without negative (N) data. Although N data is missing, it sometimes outperforms PN learning (i.e., supervised learning) in experiments. In this paper, we theoretically compare PU (and the opposite NU) learning against PN learning, and prove that, one of PU and NU learning given infinite U data will almost always improve on PN learning. Our theoretical finding is also validated experimentally.