Learning from Positive and Unlabeled Data with Arbitrary Positive Shift

02/24/2020
by   Zayd Hammoudeh, et al.
0

Positive-unlabeled (PU) learning trains a binary classifier using only positive and unlabeled data. A common simplifying assumption is that the positive data is representative of the target positive class. This assumption is often violated in practice due to time variation, domain shift, or adversarial concept drift. This paper shows that PU learning is possible even with arbitrarily non-representative positive data when provided unlabeled datasets from the source and target distributions. Our key insight is that only the negative class's distribution need be fixed. We propose two methods to learn under such arbitrary positive bias. The first couples negative-unlabeled (NU) learning with unlabeled-unlabeled (UU) learning while the other uses a novel recursive risk estimator robust to positive shift. Experimental results demonstrate our methods' effectiveness across numerous real-world datasets and forms of positive data bias, including disjoint positive class-conditional supports.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/08/2021

A Novel Perspective for Positive-Unlabeled Learning via Noisy Labels

Positive-unlabeled learning refers to the process of training a binary c...
research
10/27/2022

Learning One-Class Hyperspectral Classifier from Positive and Unlabeled Data for Low Proportion Target

Hyperspectral imagery (HSI) one-class classification is aimed at identif...
research
03/08/2023

Automatic Debiased Learning from Positive, Unlabeled, and Exposure Data

We address the issue of binary classification from positive and unlabele...
research
09/06/2023

Community-Based Hierarchical Positive-Unlabeled (PU) Model Fusion for Chronic Disease Prediction

Positive-Unlabeled (PU) Learning is a challenge presented by binary clas...
research
03/10/2016

Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learning

In PU learning, a binary classifier is trained from positive (P) and unl...
research
08/07/2018

Instance-Dependent PU Learning by Bayesian Optimal Relabeling

When learning from positive and unlabelled data, it is a strong assumpti...
research
10/05/2020

Temporal Positive-unlabeled Learning for Biomedical Hypothesis Generation via Risk Estimation

Understanding the relationships between biomedical terms like viruses, d...

Please sign up or login with your details

Forgot password? Click here to reset