Corpus ID: 126764796

DEDPUL: Method for Mixture Proportion Estimation and Positive-Unlabeled Classification based on Density Estimation

@article{Ivanov2019DEDPULMF,
  title={DEDPUL: Method for Mixture Proportion Estimation and Positive-Unlabeled Classification based on Density Estimation},
  author={Dmitry Ivanov},
  journal={ArXiv},
  year={2019},
  volume={abs/1902.06965}
}

Dmitry Ivanov

Published 2019

Computer Science

ArXiv

This paper studies Positive-Unlabeled Classification, the problem of semi-supervised binary classification in the case when Negative (N) class in the training set is contaminated with instances of Positive (P) class. We develop a novel method (DEDPUL) that simultaneously solves two problems concerning the contaminated Unlabeled (U) sample: estimates the proportions of the mixing components (P and N) in U, and classifies U. By conducting experiments on synthetic and real-world data we favorably… CONTINUE READING

Save to Library

Create Alert

Cite

Launch Research Feed