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

作者：

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.

摘要

•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.

论文关键词：Probabilistic models,Semi-supervised learning,Variational autoencoders,Predictive uncertainty

论文评审过程：Received 21 May 2019, Revised 22 October 2019, Accepted 10 December 2019, Available online 14 December 2019, Version of Record 27 December 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.107156