Isolating Latent Structure with Cross-population Variational Autoencoders
A significant body of recent work has examined variational autoencoders as a powerful approach for tasks which involve modeling the distribution of complex data such as images and text. In this work, we present a framework for modeling multiple data sets which come from differing distributions but which share some common latent structure. By incorporating architectural constraints and using a mutual information regularized form of the variational objective, our method successfully models differing data populations while explicitly encouraging the isolation of the shared and private latent factors. This enables our model to learn useful shared structure across similar tasks and to disentangle cross-population representations in a weakly supervised way. We demonstrate the utility of our method on several applications including image denoising, sub-group discovery, and continual learning.
PDF Abstract