Timezone: »

 
Oral
Isolating Sources of Disentanglement in Variational Autoencoders
Tian Qi Chen · Xuechen Li · Roger Grosse · David Duvenaud

Wed Dec 05 12:50 PM -- 01:05 PM (PST) @ Room 220 E

We decompose the evidence lower bound to show the existence of a term measuring the total correlation between latent variables. We use this to motivate the beta-TCVAE (Total Correlation Variational Autoencoder) algorithm, a refinement and plug-in replacement of the beta-VAE for learning disentangled representations, requiring no additional hyperparameters during training. We further propose a principled classifier-free measure of disentanglement called the mutual information gap (MIG). We perform extensive quantitative and qualitative experiments, in both restricted and non-restricted settings, and show a strong relation between total correlation and disentanglement, when the model is trained using our framework.

Author Information

Ricky Tian Qi Chen (University of Toronto)
Chen Li (University of Toronto)
Roger Grosse (University of Toronto)
David Duvenaud (University of Toronto)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors