Bayesian Semisupervised Learning with Deep Generative Models [article]

Jonathan Gordon, José Miguel Hernández-Lobato
2017 arXiv   pre-print
Neural network based generative models with discriminative components are a powerful approach for semi-supervised learning. However, these techniques a) cannot account for model uncertainty in the estimation of the model's discriminative component and b) lack flexibility to capture complex stochastic patterns in the label generation process. To avoid these problems, we first propose to use a discriminative component with stochastic inputs for increased noise flexibility. We show how an
more » ... Gibbs sampling procedure can marginalize the stochastic inputs when inferring missing labels in this model. Following this, we extend the discriminative component to be fully Bayesian and produce estimates of uncertainty in its parameter values. This opens the door for semi-supervised Bayesian active learning.
arXiv:1706.09751v1 fatcat:4uobcisytrdh5pcwje6aigongq