Learning disentangled representations with semi-supervised deep generative models
View / Open Files
Authors
Narayanaswamy, Siddharth
Paige, Timothy
Van de Meent, Jan-Willem
Desmaison, Alban
Goodman, Noah
Kohli, Pushmeet
Wood, Frank
Torr, Philip
Publication Date
2018-06Journal Title
Proceedings of the 31st International Conference on Neural Information Processing Systems
Conference Name
31st Conference on Neural Information Processing Systems
ISBN
9781510860964
Publisher
Curran Associates Inc.
Pages
5927-5937
Language
English
Type
Conference Object
This Version
AM
Metadata
Show full item recordCitation
Narayanaswamy, S., Paige, T., Van de Meent, J., Desmaison, A., Goodman, N., Kohli, P., Wood, F., & et al. (2018). Learning disentangled representations with semi-supervised deep generative models. Proceedings of the 31st International Conference on Neural Information Processing Systems, 5927-5937. https://doi.org/10.17863/CAM.42159
Abstract
Variational autoencoders (VAEs) learn representations of data by jointly training a probabilistic encoder and decoder network. Typically these models encode all features of the data into a single variable. Here we are interested in learning disentangled representations that encode distinct aspects of the data into separate variables. We propose to learn such representations using model architectures that generalise from standard VAEs, employing a general graphical model structure in the encoder and decoder. This allows us to train partially-specified models that make relatively strong assumptions about a subset of interpretable variables and rely on the flexibility of neural networks to learn representations for the remaining variables. We further define a general objective for semi-supervised learning in this model class, which can be approximated using an importance sampling procedure. We evaluate our framework's ability to learn disentangled representations, both by qualitative exploration of its generative capacity, and quantitative evaluation of its discriminative ability on a variety of models and datasets.
Sponsorship
Alan Turing Institute (AT/I00009/16)
Identifiers
External DOI: https://doi.org/10.17863/CAM.42159
This record's URL: https://www.repository.cam.ac.uk/handle/1810/295082
Rights
Licence:
http://www.rioxx.net/licenses/all-rights-reserved
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.