Multi-Facet Clustering Variational Autoencoders

by   Fabian Falck, et al.

Work in deep clustering focuses on finding a single partition of data. However, high-dimensional data, such as images, typically feature multiple interesting characteristics one could cluster over. For example, images of objects against a background could be clustered over the shape of the object and separately by the colour of the background. In this paper, we introduce Multi-Facet Clustering Variational Autoencoders (MFCVAE), a novel class of variational autoencoders with a hierarchy of latent variables, each with a Mixture-of-Gaussians prior, that learns multiple clusterings simultaneously, and is trained fully unsupervised and end-to-end. MFCVAE uses a progressively-trained ladder architecture which leads to highly stable performance. We provide novel theoretical results for optimising the ELBO analytically with respect to the categorical variational posterior distribution, and corrects earlier influential theoretical work. On image benchmarks, we demonstrate that our approach separates out and clusters over different aspects of the data in a disentangled manner. We also show other advantages of our model: the compositionality of its latent space and that it provides controlled generation of samples.



There are no comments yet.


page 7

page 8

page 10

page 37

page 39

page 40

page 41


Disentangling to Cluster: Gaussian Mixture Variational Ladder Autoencoders

In clustering we normally output one cluster variable for each datapoint...

Variational Clustering: Leveraging Variational Autoencoders for Image Clustering

Recent advances in deep learning have shown their ability to learn stron...

Invariance-based Multi-Clustering of Latent Space Embeddings for Equivariant Learning

Variational Autoencoders (VAEs) have been shown to be remarkably effecti...

Deep Clustering of Compressed Variational Embeddings

Motivated by the ever-increasing demands for limited communication bandw...

Deep Unsupervised Clustering Using Mixture of Autoencoders

Unsupervised clustering is one of the most fundamental challenges in mac...

Perturbation theory approach to study the latent space degeneracy of Variational Autoencoders

The use of Variational Autoencoders in different Machine Learning tasks ...

InfoVAE: Information Maximizing Variational Autoencoders

It has been previously observed that variational autoencoders tend to ig...

Code Repositories


💊 Multi-Facet Clustering Variatonal Autoencoders (MFCVAE)💊 A class of variational autoencoders to find multiple disentangled clusterings of data. Official PyTorch implementation.

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.