VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning

Akash Srivastava, Lazar Valkov, Chris Russell, Michael U. Gutmann, Charles Sutton

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


Deep generative models provide powerful tools for distributions over complicated manifolds, such as those of natural images. But many of these methods, including generative adversarial networks (GANs), can be difficult to train, in part because they are prone to mode collapse, which means that they characterize only a few modes of the true distribution. To address this, we introduce VEEGAN, which features a reconstructor network, reversing the action of the generator by mapping from data to noise. Our training objective retains the original asymptotic consistency guarantee of GANs, and can be interpreted as a novel autoencoder loss over the noise. In sharp contrast to a traditional autoencoder over data points, VEEGAN does not require specifying a loss function over the data, but rather only over the representations, which are standard normal by assumption. On an extensive set of synthetic and real world image datasets, VEEGAN indeed resists mode collapsing to a far greater extent than other recent GAN variants, and produces more realistic samples.
Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems 30 (NIPS 2017)
Place of PublicationLong Beach, CA, USA
PublisherNeural Information Processing Systems
Number of pages11
Publication statusPublished - 9 Dec 2017
EventNIPS 2017: 31st Conference on Neural Information Processing Systems - Long Beach, California, United States
Duration: 4 Dec 20179 Dec 2017

Publication series

NameAdvances in Neural Information Processing Systems
ISSN (Electronic)1049-5258


ConferenceNIPS 2017
Abbreviated titleNIPS 2017
Country/TerritoryUnited States
Internet address

Cite this