Conference item icon

Conference item

Learning disentangled representations with semi-supervised deep generative models

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 enco...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed
Version:
Accepted manuscript

Actions


Access Document


Files:

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Van De Meent, JW More by this author
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Goodman, ND More by this author
Expand authors...
More from this funder
Funding agency for:
Van De Meent, JW
Expand funders...
Publisher:
Curran Associates Publisher's website
Volume:
30
Pages:
5927-5937
Publication date:
2018-06-01
Acceptance date:
2017-09-04
Pubs id:
pubs:854010
URN:
uri:128e9b3b-b303-4bdf-a849-72cab89b3635
UUID:
uuid:128e9b3b-b303-4bdf-a849-72cab89b3635
Local pid:
pubs:854010
ISBN:
9781510860964

Terms of use


Metrics



If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP