Semi-Conditional Normalizing Flows for Semi-Supervised Learning
Machine Learning
2020-06-23 v4 Machine Learning
Abstract
This paper proposes a semi-conditional normalizing flow model for semi-supervised learning. The model uses both labelled and unlabeled data to learn an explicit model of joint distribution over objects and labels. Semi-conditional architecture of the model allows us to efficiently compute a value and gradients of the marginal likelihood for unlabeled objects. The conditional part of the model is based on a proposed conditional coupling layer. We demonstrate performance of the model for semi-supervised classification problem on different datasets. The model outperforms the baseline approach based on variational auto-encoders on MNIST dataset.
Cite
@article{arxiv.1905.00505,
title = {Semi-Conditional Normalizing Flows for Semi-Supervised Learning},
author = {Andrei Atanov and Alexandra Volokhova and Arsenii Ashukha and Ivan Sosnovik and Dmitry Vetrov},
journal= {arXiv preprint arXiv:1905.00505},
year = {2020}
}