Command Palette
Search for a command to run...
Pavel Izmailov; Polina Kirichenko; Marc Finzi; Andrew Gordon Wilson
Abstract
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.
Code Repositories
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| semi-supervised-text-classification-on-ag-1 | FlowGMM | Accuracy (%): 82.1 |
| semi-supervised-text-classification-on-ag-1 | 3 Layer MLP | Accuracy (%): 77.5 |
| semi-supervised-text-classification-on-ag-1 | Pi Model | Accuracy (%): 80.2 |
| semi-supervised-text-classification-on-yahoo | FlowGMM | Accuracy (%): 57.9 |
| semi-supervised-text-classification-on-yahoo | Pi Model | Accuracy (%): 56.3 |
| semi-supervised-text-classification-on-yahoo | 3 Layer MLP | Accuracy (%): 55.7 |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.