Semi-supervised AUC optimization based on positive-unlabeled learning
From MaRDI portal
Abstract: Maximizing the area under the receiver operating characteristic curve (AUC) is a standard approach to imbalanced classification. So far, various supervised AUC optimization methods have been developed and they are also extended to semi-supervised scenarios to cope with small sample problems. However, existing semi-supervised AUC optimization methods rely on strong distributional assumptions, which are rarely satisfied in real-world problems. In this paper, we propose a novel semi-supervised AUC optimization method that does not require such restrictive assumptions. We first develop an AUC optimization method based only on positive and unlabeled data (PU-AUC) and then extend it to semi-supervised learning by combining it with a supervised AUC optimization method. We theoretically prove that, without the restrictive distributional assumptions, unlabeled data contribute to improving the generalization performance in PU and semi-supervised AUC optimization methods. Finally, we demonstrate the practical usefulness of the proposed methods through experiments.
Recommendations
- Optimizing area under the ROC curve using semi-supervised learning
- One-pass AUC optimization
- Support vector algorithms for optimizing the partial area under the ROC curve
- Dual coordinate descent methods for solving AUC optimization problem
- Principled analytic classifier for positive-unlabeled learning via weighted integral probability metric
Cites work
- scientific article; zbMATH DE number 1332320 (Why is no real title available?)
- Block coordinate descent algorithms for large-scale sparse multiclass classification
- Class-prior estimation for learning from positive and unlabeled data
- Confidence-weighted linear classification for text categorization
- Convexity, Classification, and Risk Bounds
- Lower Bounds for the Empirical Minimization Algorithm
- One-pass AUC optimization
- Projected estimators for robust semi-supervised classification
- Soft margins for AdaBoost
Cited in
(5)- Correction to: ``Semi-supervised AUC optimization based on positive-unlabeled learning
- Optimizing area under the ROC curve using semi-supervised learning
- Dual coordinate descent methods for solving AUC optimization problem
- Triply stochastic gradient method for large-scale nonlinear similar unlabeled classification
- Anomaly detection with inexact labels
This page was built for publication: Semi-supervised AUC optimization based on positive-unlabeled learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1640567)
