Combining deep generative and discriminative models for Bayesian semi-supervised learning. (April 2020)

• Record Type: Journal Article
• Authors: Gordon, Jonathan; Hernández-Lobato, José Miguel
• Is Part Of: Pattern recognition. Volume 100(2020:Apr.)
• Publication Date: 2020-04
• Subjects: Probabilistic models -- Semi-supervised learning -- Variational autoencoders -- Predictive uncertainty; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2019.107156
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: 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. Abstract: 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.