Semi-Conditional Normalizing Flows for Semi-Supervised Learning
This addresses semi-supervised classification problems, offering an incremental improvement over existing methods.
The paper tackled semi-supervised learning by proposing a semi-conditional normalizing flow model that learns joint distributions from labeled and unlabeled data, resulting in outperforming a variational auto-encoder baseline on the MNIST dataset.
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.