Discond-VAE: Disentangling Continuous Factors from the Discrete

Abstract

In the real-world data, there are common variations shared by all classes (e.g. category label) and exclusive variations of each class. We propose a variant of VAE capable of disentangling both of these variations. To represent these generative factors of data, we introduce two sets of continuous latent variables, private variable and public variable. Our proposed framework models the private variable as a Mixture of Gaussian and the public variable as a Gaussian, respectively. Each mode of the private variable is responsible for a class of the discrete variable. Most of the previous attempts to integrate the discrete generative factors to disentanglement assume statistical independence between the continuous and discrete variables. Our proposed model, which we call Discond-VAE, DISentangles the class-dependent CONtinuous factors from the Discrete factors by introducing the private variables. The experiments show that Discond-VAE can discover the private and public factors from data. Moreover, even under the dataset with only public factors, Discond-VAE does not fail and adapts the private variables to represent the public factors.

References in corpus (14)

• Categorical Reparameterization with Gumbel-Softmax
• Neural Discrete Representation Learning
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
• Disentangling by Factorising
• Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
• Understanding disentangling in $\beta$-VAE
• Learning Deep Disentangled Embeddings with the F-Statistic Loss
• Structured Disentangled Representations
• Nonparametric Variational Auto-encoders for Hierarchical Representation Learning
• Learning Discrete and Continuous Factors of Data via Alternating Disentanglement
• Efficient end-to-end learning for quantizable representations
• InfoCatVAE: Representation Learning with Categorical Variational Autoencoders
• Variational Learning with Disentanglement-PyTorch

Cited by in corpus (1)

• Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement