Isolating Sources of Disentanglement in Variational Autoencoders
By: Researcher
Disclaimer: The provided code links for this paper are external links. Science Nest has no responsibility for the accuracy, legality or content of these links. Also, by downloading this code(s), you agree to comply with the terms of use as set out by the author(s) of the code(s).
Please contact us in case of a broken link from here
| Authors | Xuechen Li, David Duvenaud, Roger Grosse, Ricky T. Q. Chen |
| Journal/Conference Name | NeurIPS 2018 12 |
| Paper Category | Artificial Intelligence |
| Paper Abstract | We decompose the evidence lower bound to show the existence of a term measuring the total correlation between latent variables. We use this to motivate our $\beta$-TCVAE (Total Correlation Variational Autoencoder), a refinement of the state-of-the-art $\beta$-VAE objective for learning disentangled representations, requiring no additional hyperparameters during training. We further propose a principled classifier-free measure of disentanglement called the mutual information gap (MIG). We perform extensive quantitative and qualitative experiments, in both restricted and non-restricted settings, and show a strong relation between total correlation and disentanglement, when the latent variables model is trained using our framework. |
| Date of publication | 2018 |
| Code Programming Language | Multiple |
| Comment |
Copyright Researcher 2022