A Novel Perspective for Positive-Unlabeled Learning via Noisy Labels

TL;DR

This paper introduces a novel approach to positive-unlabeled learning by treating unlabeled data as noisy labels, employing joint optimization and pseudo-labeling, leading to improved performance over existing methods.

Contribution

The paper proposes a new perspective and methodology for PU learning by modeling unlabeled data as noisy labels and optimizing jointly, which enhances classification accuracy.

Findings

Outperforms state-of-the-art methods on benchmark datasets

Effective pseudo-labeling of unlabeled data improves learning

Joint optimization of noisy labels enhances model robustness

Abstract

Positive-unlabeled learning refers to the process of training a binary classifier using only positive and unlabeled data. Although unlabeled data can contain positive data, all unlabeled data are regarded as negative data in existing positive-unlabeled learning methods, which resulting in diminishing performance. We provide a new perspective on this problem -- considering unlabeled data as noisy-labeled data, and introducing a new formulation of PU learning as a problem of joint optimization of noisy-labeled data. This research presents a methodology that assigns initial pseudo-labels to unlabeled data which is used as noisy-labeled data, and trains a deep neural network using the noisy-labeled data. Experimental results demonstrate that the proposed method significantly outperforms the state-of-the-art methods on several benchmark datasets.