Poster
Isolating Sources of Disentanglement in Variational Autoencoders
Tian Qi Chen · Xuechen (Chen) Li · Roger Grosse · David Duvenaud
Room 210 #58
Keywords: [ Representation Learning ] [ Generative Models ] [ Deep Autoencoders ] [ Unsupervised Learning ] [ Variational Inference ]
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.
Live content is unavailable. Log in and register to view live content