# Variational Auto Encoder Gradient Clustering

arXiv: https://arxiv.org/abs/2105.06246 · HTML: https://mlsanity.com/paper/2105.06246/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 29 references that are in the map.
- First posted on arXiv 11 May 2021.

## Builds on (most cited first, 12 of 12)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [Semi-Supervised Learning with Deep Generative Models](https://mlsanity.com/paper/1406.5298/) (2014)
- [Adversarial Autoencoders](https://mlsanity.com/paper/1511.05644/) (2015)
- [Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering](https://mlsanity.com/paper/1611.05148/) (2016)
- [Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer](https://mlsanity.com/paper/1807.07543/) (2018)
- [Auxiliary Deep Generative Models](https://mlsanity.com/paper/1602.05473/) (2016)
- [Stick-Breaking Variational Autoencoders](https://mlsanity.com/paper/1605.06197/) (2016)
- [PixelGAN Autoencoders](https://mlsanity.com/paper/1706.00531/) (2017)
- [Optimal transport maps for distribution preserving operations on latent spaces of Generative Models](https://mlsanity.com/paper/1711.01970/) (2017)
- [On the Convergence of the Mean Shift Algorithm in the One-Dimensional Space](https://mlsanity.com/paper/1407.2961/) (2014)

## Built on by (most cited first, 1 of 1)

- [Unsupervised Statistical Learning for Die Analysis in Ancient Numismatics](https://mlsanity.com/paper/2112.00290/) (2021)

## Abstract (arXiv)

Clustering using deep neural network models have been extensively studied in recent years. Among the most popular frameworks are the VAE and GAN frameworks, which learns latent feature representations of data through encoder / decoder neural net structures. This is a suitable base for clustering tasks, as the latent space often seems to effectively capture the inherent essence of data, simplifying its manifold and reducing noise. In this article, the VAE framework is used to investigate how probability function gradient ascent over data points can be used to process data in order to achieve better clustering. Improvements in classification is observed comparing with unprocessed data, although state of the art results are not obtained. Processing data with gradient descent however results in more distinct cluster separation, making it simpler to investigate suitable hyper parameter settings such as the number of clusters. We propose a simple yet effective method for investigating suitable number of clusters for data, based on the DBSCAN clustering algorithm, and demonstrate that cluster number determination is facilitated with gradient processing. As an additional curiosity, we find that our baseline model used for comparison; a GMM on a t-SNE latent space for a VAE structure with weight one on reconstruction during training (autoencoder), yield state of the art results on the MNIST data, to our knowledge not beaten by any other existing model.