Learning Disentangled Representations with Semi-Supervised Deep Generative Models

N. Siddharth, Brooks Paige, Jan-Willem van de Meent, Alban Desmaison, Noah Goodman, Pushmeet Kohli, Frank Wood, Philip H.S. Torr

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

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.
Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems
EditorsI. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, R. Garnett
PublisherNeural Information Processing Systems
Number of pages11
Publication statusPublished - 9 Dec 2017
EventThirty-first Annual Conference on Neural Information Processing Systems - Long Beach Convention Center, Long Beach, United States
Duration: 4 Dec 20179 Dec 2017

Publication series

ISSN (Electronic)1049-5258


ConferenceThirty-first Annual Conference on Neural Information Processing Systems
Abbreviated titleNIPS
Country/TerritoryUnited States
CityLong Beach


Dive into the research topics of 'Learning Disentangled Representations with Semi-Supervised Deep Generative Models'. Together they form a unique fingerprint.

Cite this