Dissimilarity Mixture Autoencoder for Deep Clustering (2020-06-15T00:00:00.000000Z)

TL;DR

A novel neural network model that uses a dissimilarity function to generalize a family of density estimation and clustering methods and can leverage from deep representation learning due to its straightforward incorporation into deep learning architectures.

Abstract

In this paper, we introduce the Dissimilarity Mixture Autoencoder (DMAE), a novel neural network model that uses a dissimilarity function to generalize a family of density estimation and clustering methods. It is formulated in such a way that it internally estimates the parameters of a probability distribution through gradient-based optimization. Also, the proposed model can leverage from deep representation learning due to its straightforward incorporation into deep learning architectures, because, it consists of an encoder-decoder network that computes a probabilistic representation. Experimental evaluation was performed on image and text clustering benchmark datasets showing that the method is competitive in terms of unsupervised classification accuracy and normalized mutual information. The source code to replicate the experiments is publicly available at this https URL

Authors

Juan S. Lara

1 papers

F. A. Gonz'alez

1 papers

TL;DR

Abstract

Authors

References39 items

Generative Adversarial Networks

Deep Clustering by Gaussian Mixture Variational Autoencoders With Graph Embedding

Semi-supervised deep embedded clustering

Deep Density-based Image Clustering

Deep Embedded Clustering with Data Augmentation

Gaussian Mixture Models

ClusterGAN : Latent Space Clustering in Generative Adversarial Networks

Clustering with Deep Learning: Taxonomy and New Methods

SpectralNet: Spectral Clustering using Deep Neural Networks

Deep Clustering with Convolutional Autoencoders

Scalable Kernel K-Means Clustering with Nystrom Approximation: Relative-Error Bounds

Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization

Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations

Discriminatively Boosted Image Clustering with Fully Convolutional Auto-Encoders

Learning Discrete Representations via Information Maximizing Self-Augmented Training

Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering

Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders

Categorical Reparameterization with Gumbel-Softmax

Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering

InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets

Joint Unsupervised Learning of Deep Representations and Image Clusters

Composing graphical models with neural networks for structured representations and fast inference

Unsupervised Deep Embedding for Clustering Analysis

Auto-Encoding Variational Bayes

Efficient Kernel Clustering Using Random Fourier Features

A simple and fast algorithm for K-medoids clustering

Discriminative K-means for Clustering

Random Features for Large-Scale Kernel Machines

Clustering by Passing Messages Between Data Points

Pattern Recognition and Machine Learning

Clustering with Bregman Divergences

Kernel k-means: spectral clustering and normalized cuts

On Spectral Clustering: Analysis and an algorithm

Methods of combining multiple classifiers and their applications to handwriting recognition

Hierarchical clustering schemes

Deep embedding clustering based on contractive autoencoder

This PDF file includes: Materials and Methods

Cascading classifiers

FCM: The fuzzy c-means clustering algorithm

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names