Bounded Information Rate Variational Autoencoders
This addresses the need for more interpretable and efficient latent representations in generative models, though it is incremental as it builds on existing VAE frameworks.
The paper tackles the problem of controlling information flow in Variational Autoencoders by introducing a bounded information rate constraint, resulting in a model that provides a meaningful latent representation with specifiable bit resolution and achieves performance comparable to state-of-the-art methods with lower computational complexity.
This paper introduces a new member of the family of Variational Autoencoders (VAE) that constrains the rate of information transferred by the latent layer. The latent layer is interpreted as a communication channel, the information rate of which is bound by imposing a pre-set signal-to-noise ratio. The new constraint subsumes the mutual information between the input and latent variables, combining naturally with the likelihood objective of the observed data as used in a conventional VAE. The resulting Bounded-Information-Rate Variational Autoencoder (BIR-VAE) provides a meaningful latent representation with an information resolution that can be specified directly in bits by the system designer. The rate constraint can be used to prevent overtraining, and the method naturally facilitates quantisation of the latent variables at the set rate. Our experiments confirm that the BIR-VAE has a meaningful latent representation and that its performance is at least as good as state-of-the-art competing algorithms, but with lower computational complexity.