Poster
Learning Disentangled Representations with Semi-Supervised Deep Generative Models
Siddharth Narayanaswamy · Brooks Paige · Jan-Willem van de Meent · Alban Desmaison · Noah Goodman · Pushmeet Kohli · Frank Wood · Philip Torr

Mon Dec 4th 06:30 -- 10:30 PM @ Pacific Ballroom #184 #None

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.

Author Information

Siddharth Narayanaswamy (University of Oxford)
Brooks Paige (Alan Turing Institute)
Jan-Willem van de Meent (Northeastern University)
Alban Desmaison (Oxford University)
Noah Goodman (Stanford University)
Pushmeet Kohli (Microsoft Research)
Frank Wood (University of British Columbia)

Dr. Wood is an associate professor in the Department of Engineering Science at the University of Oxford. Before that he was an assistant professor of Statistics at Columbia University and a research scientist at the Columbia Center for Computational Learning Systems. He formerly was a postdoctoral fellow of the Gatsby Computational Neuroscience Unit of the University College London. He holds a PhD from Brown University (’07) and BS from Cornell University (’96), both in computer science. Dr. Wood is the original architect of both the Anglican and Probabilistic-C probabilistic programming systems. He conducts AI-driven research at the boundary of probabilistic programming, Bayesian modeling, and Monte Carlo methods. Dr. Wood holds 6 patents, has authored over 50 papers, received the AISTATS best paper award in 2009, and has been awarded faculty research awards from Xerox, Google and Amazon. Prior to his academic career he was a successful entrepreneur having run and sold the content-based image retrieval company ToFish! to AOL/Time Warner and served as CEO of Interfolio.

Philip Torr (University of Oxford)

More from the Same Authors