Learning from positive and unlabeled data: a survey

DOI10.1007/s10994-020-05877-5zbMath1496.68270arXiv1811.04820OpenAlexW3101215053MaRDI QIDQ782438

Jessa Bekker, Jesse Davis

Publication date: 27 July 2020

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1811.04820

zbMATH Keywords

classificationweakly supervised learningPU learning

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05) Research exposition (monographs, survey articles) pertaining to computer science (68-02)

Related Items (11)

A hard EM algorithm for prediction of the cured fraction in survival data ⋮ Revisiting strategies for fitting logistic regression for positive and unlabeled data ⋮ Joint feature selection and classification for positive unlabelled multi-label data using weighted penalized empirical risk minimization ⋮ Estimating the class prior for positive and unlabelled data via logistic regression ⋮ A two-step anomaly detection based method for PU classification in imbalanced data sets ⋮ Learning Distributional Programs for Relational Autocompletion ⋮ Adaptive novelty detection with false discovery rate guarantee ⋮ Active learning for hierarchical multi-label classification ⋮ Noisy label tolerance: a new perspective of partial multi-label learning ⋮ Optimised one-class classification performance ⋮ A network-based positive and unlabeled learning approach for fake news detection

Uses Software

• Aleph
• ProDiGe

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Classification with asymmetric label noise: consistency and maximal denoising
• Semi-supervised learning of class balance under class-prior change by distribution matching
• Simple strategies for semi-supervised feature selection
• Laplacian unit-hyperplane learning from positive and unlabeled examples
• Not so naive Bayes: Aggregating one-dependence estimators
• A biased least squares support vector machine based on Mahalanobis distance for PU learning
• Positive and unlabeled relational classification through label frequency estimation
• Class-prior estimation for learning from positive and unlabeled data
• Dealing with under-reported variables: an information theoretic solution
• Learning from positive and unlabeled examples
• Estimating logistic regression models when the dependent variable has no variance
• Presence‐Only Data and the EM Algorithm
• Inference and missing data
• Single-class classification with mapping convergence
• Random forests

This page was built for publication: Learning from positive and unlabeled data: a survey