pith. sign in

Implicit Autoencoders

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

In this paper, we describe the "implicit autoencoder" (IAE), a generative autoencoder in which both the generative path and the recognition path are parametrized by implicit distributions. We use two generative adversarial networks to define the reconstruction and the regularization cost functions of the implicit autoencoder, and derive the learning rules based on maximum-likelihood learning. Using implicit distributions allows us to learn more expressive posterior and conditional likelihood distributions for the autoencoder. Learning an expressive conditional likelihood distribution enables the latent code to only capture the abstract and high-level information of the data, while the remaining low-level information is captured by the implicit conditional likelihood distribution. We show the applications of implicit autoencoders in disentangling content and style information, clustering, semi-supervised classification, learning expressive variational distributions, and multimodal image-to-image translation from unpaired data.

fields

stat.ML 1

years

2019 1

verdicts

UNVERDICTED 1

representative citing papers

Node Attribute Generation on Graphs

stat.ML · 2019-07-23 · unverdicted · novelty 4.0

NANG uses adversarial learning to generate unobserved node attributes from graph structure via a shared latent space.

citing papers explorer

Showing 1 of 1 citing paper.

  • Node Attribute Generation on Graphs stat.ML · 2019-07-23 · unverdicted · none · ref 23 · internal anchor

    NANG uses adversarial learning to generate unobserved node attributes from graph structure via a shared latent space.