Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders

11/08/2016
by   Nat Dilokthanakul, et al.
0

We study a variant of the variational autoencoder model (VAE) with a Gaussian mixture as a prior distribution, with the goal of performing unsupervised clustering through deep generative models. We observe that the known problem of over-regularisation that has been shown to arise in regular VAEs also manifests itself in our model and leads to cluster degeneracy. We show that a heuristic called minimum information constraint that has been shown to mitigate this effect in VAEs can also be applied to improve unsupervised clustering performance with our model. Furthermore we analyse the effect of this heuristic and provide an intuition of the various processes with the help of visualizations. Finally, we demonstrate the performance of our model on synthetic data, MNIST and SVHN, showing that the obtained clusters are distinct, interpretable and result in achieving competitive performance on unsupervised clustering to the state-of-the-art results.

READ FULL TEXT
research
10/17/2019

Mixture-of-Experts Variational Autoencoder for clustering and generating from similarity-based representations

Clustering high-dimensional data, such as images or biological measureme...
research
05/10/2020

Variational Clustering: Leveraging Variational Autoencoders for Image Clustering

Recent advances in deep learning have shown their ability to learn stron...
research
02/11/2019

Variational Autoencoder with Truncated Mixture of Gaussians for Functional Connectivity Analysis

Resting-state functional connectivity states are often identified as clu...
research
09/05/2018

Stellar Cluster Detection using GMM with Deep Variational Autoencoder

Detecting stellar clusters have always been an important research proble...
research
08/16/2019

Regression on imperfect class labels derived by unsupervised clustering

Outcome regressed on class labels identified by unsupervised clustering ...
research
06/11/2021

Deep Conditional Gaussian Mixture Model for Constrained Clustering

Constrained clustering has gained significant attention in the field of ...
research
12/07/2020

Joint Optimization of an Autoencoder for Clustering and Embedding

Incorporating k-means-like clustering techniques into (deep) autoencoder...

Please sign up or login with your details

Forgot password? Click here to reset