MixPUL: Consistency-based Augmentation for Positive and Unlabeled Learning

04/20/2020
by   Tong Wei, et al.
0

Learning from positive and unlabeled data (PU learning) is prevalent in practical applications where only a couple of examples are positively labeled. Previous PU learning studies typically rely on existing samples such that the data distribution is not extensively explored. In this work, we propose a simple yet effective data augmentation method, coined , based on consistency regularization which provides a new perspective of using PU data. In particular, the proposed  incorporates supervised and unsupervised consistency training to generate augmented data. To facilitate supervised consistency, reliable negative examples are mined from unlabeled data due to the absence of negative samples. Unsupervised consistency is further encouraged between unlabeled datapoints. In addition,  reduces margin loss between positive and unlabeled pairs, which explicitly optimizes AUC and yields faster convergence. Finally, we conduct a series of studies to demonstrate the effectiveness of consistency regularization. We examined three kinds of reliable negative mining methods. We show that  achieves an averaged improvement of classification error from 16.49 to 13.09 on the CIFAR-10 dataset across different positive data amount.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/06/2022

Dist-PU: Positive-Unlabeled Learning from a Label Distribution Perspective

Positive-Unlabeled (PU) learning tries to learn binary classifiers from ...
research
11/05/2016

Class-prior Estimation for Learning from Positive and Unlabeled Data

We consider the problem of estimating the class prior in an unlabeled da...
research
10/22/2020

Unsupervised Data Augmentation with Naive Augmentation and without Unlabeled Data

Unsupervised Data Augmentation (UDA) is a semi-supervised technique that...
research
11/30/2022

Split-PU: Hardness-aware Training Strategy for Positive-Unlabeled Learning

Positive-Unlabeled (PU) learning aims to learn a model with rare positiv...
research
01/29/2019

Revisiting Sample Selection Approach to Positive-Unlabeled Learning: Turning Unlabeled Data into Positive rather than Negative

In the early history of positive-unlabeled (PU) learning, the sample sel...
research
04/21/2020

Improving Positive Unlabeled Learning: Practical AUL Estimation and New Training Method for Extremely Imbalanced Data Sets

Positive Unlabeled (PU) learning is widely used in many applications, wh...
research
11/28/2016

Exploiting Unlabeled Data for Neural Grammatical Error Detection

Identifying and correcting grammatical errors in the text written by non...

Please sign up or login with your details

Forgot password? Click here to reset