Combining deep generative and discriminative models for Bayesian semi-supervised learning

•Modelling framwork that enables Bayesian semi-supervised learning.•Bayesian semi-supervised improves overall performance and uncertainty calibration.•Models generalize standard deep generative models for semi-supervised learning. Generative models can be used for a wide range of tasks, and have the...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Pattern recognition Ročník 100; s. 107156
Hlavní autori: Gordon, Jonathan, Hernández-Lobato, José Miguel
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier Ltd 01.04.2020
Predmet:
Predictive uncertainty
Probabilistic models
Semi-supervised learning
Variational autoencoders
Variational autoencoders
Probabilistic models
Predictive uncertainty
Semi-supervised learning
ISSN:0031-3203, 1873-5142
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:•Modelling framwork that enables Bayesian semi-supervised learning.•Bayesian semi-supervised improves overall performance and uncertainty calibration.•Models generalize standard deep generative models for semi-supervised learning. Generative models can be used for a wide range of tasks, and have the appealing ability to learn from both labelled and unlabelled data. In contrast, discriminative models cannot learn from unlabelled data, but tend to outperform their generative counterparts in supervised tasks. We develop a framework to jointly train deep generative and discriminative models, enjoying the benefits of both. The framework allows models to learn from labelled and unlabelled data, as well as naturally account for uncertainty in predictive distributions, providing the first Bayesian approach to semi-supervised learning with deep generative models. We demonstrate that our blended discriminative and generative models outperform purely generative models in both predictive performance and uncertainty calibration in a number of semi-supervised learning tasks.
ISSN:0031-3203
1873-5142
DOI:10.1016/j.patcog.2019.107156