Property Controllable Variational Autoencoder via Invertible Mutual DependenceDownload PDF

28 Sept 2020, 15:51 (modified: 05 Apr 2022, 00:16)ICLR 2021 PosterReaders: Everyone
Keywords: deep generative models, interpretable latent representation, disentangled representation learning
Abstract: Deep generative models have made important progress towards modeling complex, high dimensional data via learning latent representations. Their usefulness is nevertheless often limited by a lack of control over the generative process or a poor understanding of the latent representation. To overcome these issues, attention is now focused on discovering latent variables correlated to the data properties and ways to manipulate these properties. This paper presents the new Property controllable VAE (PCVAE), where a new Bayesian model is proposed to inductively bias the latent representation using explicit data properties via novel group-wise and property-wise disentanglement. Each data property corresponds seamlessly to a latent variable, by innovatively enforcing invertible mutual dependence between them. This allows us to move along the learned latent dimensions to control specific properties of the generated data with great precision. Quantitative and qualitative evaluations confirm that the PCVAE outperforms the existing models by up to 28% in capturing and 65% in manipulating the desired properties.
One-sentence Summary: A novel generative model for learning interpretable latent representation for generating data with desired properties.
Supplementary Material: zip
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Data: [dSprites](
21 Replies