On Leveraging Unlabeled Data for Concurrent Positive-Unlabeled Classification and Robust Generation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yu, Bing, Sun, Ke, Wang, He, Lin, Zhouchen, Zhu, Zhanxing
Format: Preprint
Publié: 2020
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913957104582656
author Yu, Bing
Sun, Ke
Wang, He
Lin, Zhouchen
Zhu, Zhanxing
author_facet Yu, Bing
Sun, Ke
Wang, He
Lin, Zhouchen
Zhu, Zhanxing
contents The scarcity of class-labeled data is a ubiquitous bottleneck in many machine learning problems. While abundant unlabeled data typically exist and provide a potential solution, it is highly challenging to exploit them. In this paper, we address this problem by leveraging Positive-Unlabeled~(PU) classification and the conditional generation with extra unlabeled data \emph{simultaneously}. We present a novel training framework to jointly target both PU classification and conditional generation when exposed to extra data, especially out-of-distribution unlabeled data, by exploring the interplay between them: 1) enhancing the performance of PU classifiers with the assistance of a novel Classifier-Noise-Invariant Conditional GAN~(CNI-CGAN) that is robust to noisy labels, 2) leveraging extra data with predicted labels from a PU classifier to help the generation. Theoretically, we prove the optimal condition of CNI-CGAN and experimentally, we conducted extensive evaluations on diverse datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2006_07841
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle On Leveraging Unlabeled Data for Concurrent Positive-Unlabeled Classification and Robust Generation
Yu, Bing
Sun, Ke
Wang, He
Lin, Zhouchen
Zhu, Zhanxing
Machine Learning
The scarcity of class-labeled data is a ubiquitous bottleneck in many machine learning problems. While abundant unlabeled data typically exist and provide a potential solution, it is highly challenging to exploit them. In this paper, we address this problem by leveraging Positive-Unlabeled~(PU) classification and the conditional generation with extra unlabeled data \emph{simultaneously}. We present a novel training framework to jointly target both PU classification and conditional generation when exposed to extra data, especially out-of-distribution unlabeled data, by exploring the interplay between them: 1) enhancing the performance of PU classifiers with the assistance of a novel Classifier-Noise-Invariant Conditional GAN~(CNI-CGAN) that is robust to noisy labels, 2) leveraging extra data with predicted labels from a PU classifier to help the generation. Theoretically, we prove the optimal condition of CNI-CGAN and experimentally, we conducted extensive evaluations on diverse datasets.
title On Leveraging Unlabeled Data for Concurrent Positive-Unlabeled Classification and Robust Generation
topic Machine Learning
url https://arxiv.org/abs/2006.07841