Timezone: »

Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learning
Gang Niu · Marthinus Christoffel du Plessis · Tomoya Sakai · Yao Ma · Masashi Sugiyama

Mon Dec 05 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #157 #None

In PU learning, a binary classifier is trained from positive (P) and unlabeled (U) data without negative (N) data. Although N data is missing, it sometimes outperforms PN learning (i.e., ordinary supervised learning). Hitherto, neither theoretical nor experimental analysis has been given to explain this phenomenon. In this paper, we theoretically compare PU (and NU) learning against PN learning based on the upper bounds on estimation errors. We find simple conditions when PU and NU learning are likely to outperform PN learning, and we prove that, in terms of the upper bounds, either PU or NU learning (depending on the class-prior probability and the sizes of P and N data) given infinite U data will improve on PN learning. Our theoretical findings well agree with the experimental results on artificial and benchmark data even when the experimental setup does not match the theoretical assumptions exactly.

Author Information

Gang Niu (University of Tokyo)

Gang Niu is currently a research scientist (indefinite-term) at RIKEN Center for Advanced Intelligence Project. He received the PhD degree in computer science from Tokyo Institute of Technology in 2013. Before joining RIKEN as a research scientist, he was a senior software engineer at Baidu and then an assistant professor at the University of Tokyo. He has published more than 70 journal articles and conference papers, including 14 NeurIPS (1 oral and 3 spotlights), 28 ICML, and 2 ICLR (1 oral) papers. He has served as an area chair 14 times, including ICML 2019--2021, NeurIPS 2019--2021, and ICLR 2021--2022.

Marthinus Christoffel du Plessis (The University of Tokyo)
Tomoya Sakai (The University of Tokyo)
Yao Ma
Masashi Sugiyama (RIKEN / University of Tokyo)

More from the Same Authors