PRI-VAE: Principle-of-Relevant-Information Variational Autoencoders
This work addresses the challenge of understanding and improving disentangled representation learning in VAEs, which is incremental as it builds on existing VAE frameworks with a new objective and analysis.
The authors tackled the problem of learning disentangled representations in variational autoencoders (VAEs) by proposing PRI-VAE, a novel learning objective, and analyzed existing models through an information-theoretic perspective, demonstrating its effectiveness on four benchmark datasets.
Although substantial efforts have been made to learn disentangled representations under the variational autoencoder (VAE) framework, the fundamental properties to the dynamics of learning of most VAE models still remain unknown and under-investigated. In this work, we first propose a novel learning objective, termed the principle-of-relevant-information variational autoencoder (PRI-VAE), to learn disentangled representations. We then present an information-theoretic perspective to analyze existing VAE models by inspecting the evolution of some critical information-theoretic quantities across training epochs. Our observations unveil some fundamental properties associated with VAEs. Empirical results also demonstrate the effectiveness of PRI-VAE on four benchmark data sets.