On Positive-Unlabeled Classification in GAN

02/04/2020
by   Tianyu Guo, et al.
6

This paper defines a positive and unlabeled classification problem for standard GANs, which then leads to a novel technique to stabilize the training of the discriminator in GANs. Traditionally, real data are taken as positive while generated data are negative. This positive-negative classification criterion was kept fixed all through the learning process of the discriminator without considering the gradually improved quality of generated data, even if they could be more realistic than real data at times. In contrast, it is more reasonable to treat the generated data as unlabeled, which could be positive or negative according to their quality. The discriminator is thus a classifier for this positive and unlabeled classification problem, and we derive a new Positive-Unlabeled GAN (PUGAN). We theoretically discuss the global optimality the proposed model will achieve and the equivalent optimization goal. Empirically, we find that PUGAN can achieve comparable or even better performance than those sophisticated discriminator stabilization methods.

READ FULL TEXT

page 5

page 7

research
08/26/2022

Learning From Positive and Unlabeled Data Using Observer-GAN

The problem of learning from positive and unlabeled data (A.K.A. PU lear...
research
10/19/2017

Binary Classification from Positive-Confidence Data

Reducing labeling costs in supervised learning is a critical issue in ma...
research
11/25/2022

Positive unlabeled learning with tensor networks

Positive unlabeled learning is a binary classification problem with posi...
research
10/04/2019

Generating Relevant Counter-Examples from a Positive Unlabeled Dataset for Image Classification

With surge of available but unlabeled data, Positive Unlabeled (PU) lear...
research
03/18/2018

A Robust AUC Maximization Framework with Simultaneous Outlier Detection and Feature Selection for Positive-Unlabeled Classification

The positive-unlabeled (PU) classification is a common scenario in real-...
research
04/16/2019

Classification of Existing Virtualization Methods Used in Telecommunication Networks

This article studies the existing methods of virtualization of different...
research
11/21/2017

A generative adversarial framework for positive-unlabeled classification

In this work, we consider the task of classifying the binary positive-un...

Please sign up or login with your details

Forgot password? Click here to reset