Deep Unsupervised Clustering Using Mixture of Autoencoders

TL;DR

This paper introduces a novel unsupervised clustering method that leverages a mixture of autoencoders to identify and separate data manifolds, improving clustering by jointly learning data representations and cluster assignments.

Contribution

It proposes a joint optimization framework combining multiple autoencoders and a mixture assignment network for unsupervised clustering of data on nonlinear manifolds.

Findings

Effective separation of data into meaningful clusters

Simultaneous learning of data manifolds and cluster assignments

Improved clustering performance on complex datasets

Abstract

Unsupervised clustering is one of the most fundamental challenges in machine learning. A popular hypothesis is that data are generated from a union of low-dimensional nonlinear manifolds; thus an approach to clustering is identifying and separating these manifolds. In this paper, we present a novel approach to solve this problem by using a mixture of autoencoders. Our model consists of two parts: 1) a collection of autoencoders where each autoencoder learns the underlying manifold of a group of similar objects, and 2) a mixture assignment neural network, which takes the concatenated latent vectors from the autoencoders as input and infers the distribution over clusters. By jointly optimizing the two parts, we simultaneously assign data to clusters and learn the underlying manifolds of each cluster.