Revisiting Factorizing Aggregated Posterior in Learning Disentangled Representations

Abstract

In the problem of learning disentangled representations, one of the promising methods is to factorize aggregated posterior by penalizing the total correlation of sampled latent variables. However, this well-motivated strategy has a blind spot: there is a disparity between the sampled latent representation and its corresponding mean representation. In this paper, we provide a theoretical explanation that low total correlation of sampled representation cannot guarantee low total correlation of the mean representation. Indeed, we prove that for the multivariate normal distributions, the mean representation with arbitrarily high total correlation can have a corresponding sampled representation with bounded total correlation. We also propose a method to eliminate this disparity. Experiments show that our model can learn a mean representation with much lower total correlation, hence a factorized mean representation. Moreover, we offer a detailed explanation of the limitations of factorizing aggregated posterior: factor disintegration. Our work indicates a potential direction for future research of disentangled learning.

References in corpus (8)

• Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
• Disentangling by Factorising
• Estimating divergence functionals and the likelihood ratio by convex risk minimization
• Deep Variational Information Bottleneck
• Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations
• Isolating Sources of Disentanglement in Variational Autoencoders
• Learning Deep Disentangled Embeddings with the F-Statistic Loss
• Disentangling the independently controllable factors of variation by interacting with the world

Cited by in corpus (1)

• Be More Active! Understanding the Differences between Mean and Sampled Representations of Variational Autoencoders