Semi-Supervised Learning with Normalizing Flows
This work addresses semi-supervised learning for researchers and practitioners by offering a simple, interpretable method applicable beyond images, though it appears incremental as it builds on existing normalizing flow techniques.
The paper tackled the problem of semi-supervised learning by proposing FlowGMM, an end-to-end approach using normalizing flows with a latent Gaussian mixture model, which achieved promising results across diverse applications like text, tabular, and image data.
Normalizing flows transform a latent distribution through an invertible neural network for a flexible and pleasingly simple approach to generative modelling, while preserving an exact likelihood. We propose FlowGMM, an end-to-end approach to generative semi supervised learning with normalizing flows, using a latent Gaussian mixture model. FlowGMM is distinct in its simplicity, unified treatment of labelled and unlabelled data with an exact likelihood, interpretability, and broad applicability beyond image data. We show promising results on a wide range of applications, including AG-News and Yahoo Answers text data, tabular data, and semi-supervised image classification. We also show that FlowGMM can discover interpretable structure, provide real-time optimization-free feature visualizations, and specify well calibrated predictive distributions.