# Deep Generative Clustering with VAEs and Expectation-Maximization

arXiv: https://arxiv.org/abs/2501.07358 · HTML: https://mlsanity.com/paper/2501.07358/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jan 2025.

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

- [Slicing the Gaussian Mixture Wasserstein Distance](https://mlsanity.com/paper/2504.08544/) (2025)
- [From Points to Spheres: A Geometric Reinterpretation of Variational Autoencoders](https://mlsanity.com/paper/2507.17255/) (2025)
- [Dialectics for Artificial Intelligence](https://mlsanity.com/paper/2512.17373/) (2025)
- [Deep Generalised Mixed Models: a Novel Neural Network Structure for Analysing Hierarchical Data](https://mlsanity.com/paper/2608.05930/) (2026)

## Abstract (arXiv)

We propose a novel deep clustering method that integrates Variational Autoencoders (VAEs) into the Expectation-Maximization (EM) framework. Our approach models the probability distribution of each cluster with a VAE and alternates between updating model parameters by maximizing the Evidence Lower Bound (ELBO) of the log-likelihood and refining cluster assignments based on the learned distributions. This enables effective clustering and generation of new samples from each cluster. Unlike existing VAE-based methods, our approach eliminates the need for a Gaussian Mixture Model (GMM) prior or additional regularization techniques. Experiments on MNIST and FashionMNIST demonstrate superior clustering performance compared to state-of-the-art methods.