The Variational Homoencoder: Learning to learn high capacity generative models from few examples
Name
1807.08919.pdf
Description
Submitted version
Size
2.43 MB
Format
Adobe PDF
Checksum (MD5)
2200ed4676189fe116d080cf0b5cd831
Author(s)
Hewitt, Luke B.
Nye, Maxwell I.
Gane, Andreea
Jaakkola, Tommi
Tenenbaum, Joshua B.
Date Issued
2018
Citation
Hewitt, Luke B., Nye, Maxwell I., Gane, Andreea, Jaakkola, Tommi and Tenenbaum, Joshua B. 2018. "The Variational Homoencoder: Learning to learn high capacity generative models from few examples."
Version
Original manuscript
Abstract
© 34th Conference on Uncertainty in Artificial Intelligence 2018. All rights reserved. Hierarchical Bayesian methods can unify many related tasks (e.g. k-shot classification, conditional and unconditional generation) as inference within a single generative model. However, when this generative model is expressed as a powerful neural network such as a PixelCNN, we show that existing learning techniques typically fail to effectively use latent variables. To address this, we develop a modification of the Variational Autoencoder in which encoded observations are decoded to new elements from the same class. This technique, which we call a Variational Homoencoder (VHE), produces a hierarchical latent variable model which better utilises latent variables. We use the VHE framework to learn a hierarchical PixelCNN on the Omniglot dataset, which outperforms all existing models on test set likelihood and achieves strong performance on one-shot generation and classification tasks. We additionally validate the VHE on natural images from the YouTube Faces database. Finally, we develop extensions of the model that apply to richer dataset structures such as factorial and hierarchical categories.
MIT Department
MIT-IBM Watson AI Lab
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
http://auai.org/uai2018/accepted.php
