Discond-VAE: Disentangling Continuous Factors from the Discrete
This addresses the challenge of integrating discrete generative factors in disentanglement for machine learning applications, though it appears incremental as it builds on existing VAE frameworks.
The paper tackles the problem of disentangling continuous factors from discrete ones in real-world data, proposing Discond-VAE, a variant of VAE that models private and public latent variables, and shows it can discover these factors and adapt to datasets with only public factors.
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.