# VMI-VAE: Variational Mutual Information Maximization Framework for VAE With Discrete and Continuous Priors

arXiv: https://arxiv.org/abs/2005.13953 · HTML: https://mlsanity.com/paper/2005.13953/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 May 2020.

## Built on by (most cited first, 4 of 4)

- [Multi-VAE: Learning Disentangled View-common and View-peculiar Visual Representations for Multi-view Clustering](https://mlsanity.com/paper/2106.11232/) (2021)
- [Training β-VAE by Aggregating a Learned Gaussian Posterior with a Decoupled Decoder](https://mlsanity.com/paper/2209.14783/) (2022)
- [Learning Disentangled Representations for Generalized Multi-view Clustering](https://mlsanity.com/paper/2605.15640/) (2026)
- [Deep Dive into Semi-Supervised ELBO for Improving Classification Performance](https://mlsanity.com/paper/2108.12734/) (2021)

## Abstract (arXiv)

Variational Autoencoder is a scalable method for learning latent variable models of complex data. It employs a clear objective that can be easily optimized. However, it does not explicitly measure the quality of learned representations. We propose a Variational Mutual Information Maximization Framework for VAE to address this issue. It provides an objective that maximizes the mutual information between latent codes and observations. The objective acts as a regularizer that forces VAE to not ignore the latent code and allows one to select particular components of it to be most informative with respect to the observations. On top of that, the proposed framework provides a way to evaluate mutual information between latent codes and observations for a fixed VAE model.