Poster
Learning Hierarchical Priors in VAEs
Alexej Klushyn · Nutan Chen · Richard Kurle · Botond Cseke · Patrick van der Smagt
Keywords: [ Generative Models ] [ Deep Learning ] [ Probabilistic Methods; Probabilistic Methods -> Hierarchical Models; Probabilistic Methods ] [ Latent Variable Models; Probabili ]
We propose to learn a hierarchical prior in the context of variational autoencoders to avoid the over-regularisation resulting from a standard normal prior distribution. To incentivise an informative latent representation of the data, we formulate the learning problem as a constrained optimisation problem by extending the Taming VAEs framework to two-level hierarchical models. We introduce a graph-based interpolation method, which shows that the topology of the learned latent representation corresponds to the topology of the data manifold---and present several examples, where desired properties of latent representation such as smoothness and simple explanatory factors are learned by the prior.