The Variational Fair Autoencoder

3 Nov 2015  ·  Christos Louizos, Kevin Swersky, Yujia Li, Max Welling, Richard Zemel ·

We investigate the problem of learning representations that are invariant to certain nuisance or sensitive factors of variation in the data while retaining as much of the remaining information as possible. Our model is based on a variational autoencoding architecture with priors that encourage independence between sensitive and latent factors of variation. Any subsequent processing, such as classification, can then be performed on this purged latent representation. To remove any remaining dependencies we incorporate an additional penalty term based on the "Maximum Mean Discrepancy" (MMD) measure. We discuss how these architectures can be efficiently trained on data and show in experiments that this method is more effective than previous work in removing unwanted sources of variation while maintaining informative latent representations.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Sentiment Analysis Multi-Domain Sentiment Dataset VFAE DVD 76.57 # 4
Books 73.40 # 4
Electronics 80.53 # 3
Kitchen 82.93 # 4
Average 78.36 # 5


No methods listed for this paper. Add relevant methods here