Modeling PU learning using probabilistic logic programming

The goal of learning from positive and unlabeled (PU) examples is to learn a classifier that predicts the posterior class probability. The challenge is that the available labels in the data are determined by (1) the true class, and (2) the labeling mechanism that selects which positive examples get...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Machine learning Ročník 113; číslo 3; s. 1351 - 1372
Hlavní autoři: Verreet, Victor, De Raedt, Luc, Bekker, Jessa
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York Springer US 01.03.2024
Springer Nature B.V
Témata:
Artificial Intelligence
Classifiers
Computer Science
Control
Empirical analysis
Labeling
Labels
Learning
Logic programming
Machine Learning
Mechatronics
Modeling
Modelling
Natural Language Processing (NLP)
Positive unlabeled learning
Probabilistic logic programming
Robotics
Simulation and Modeling
Special Issue on Learning and Reasoning 2022
Statistical analysis
Unidentifiability
Weak supervision
Unidentifiability
Weak supervision
Positive unlabeled learning
Probabilistic logic programming
Modeling
ISSN:0885-6125, 1573-0565, 1573-0565
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The goal of learning from positive and unlabeled (PU) examples is to learn a classifier that predicts the posterior class probability. The challenge is that the available labels in the data are determined by (1) the true class, and (2) the labeling mechanism that selects which positive examples get labeled, where often certain examples have a higher probability to be selected than others. Incorrectly assuming an unbiased labeling mechanism leads to learning a biased classifier. Yet, this is what most existing methods do. A handful of methods makes more realistic assumptions, but they are either so general that it is impossible to distinguish between the effects of the true classification and of the labeling mechanism, or too restrictive to correctly model the real situation, or require knowledge that is typically unavailable. This paper studies how to formulate and integrate more realistic assumptions for learning better classifiers, by exploiting the strengths of probabilistic logic programming (PLP). Concretely, (1) we propose PU ProbLog: a PLP-based general method that allows to (partially) model the labeling mechanism. (2) We show that our method generalizes existing methods, in the sense that it can model the same assumptions. (3) Thanks to the use of PLP, our method supports also PU learning in relational domains. (4) Our empirical analysis shows that partially modeling the labeling bias, improves the learned classifiers.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0885-6125
1573-0565
1573-0565
DOI:10.1007/s10994-023-06461-3