Unsupervised Deep Embedding for Clustering Analysis

TL;DR

This paper introduces Deep Embedded Clustering (DEC), a novel method that jointly learns data representations and cluster assignments using deep neural networks, leading to improved clustering performance on images and text.

Contribution

DEC is the first approach to simultaneously learn feature representations and clustering assignments through deep neural networks.

Findings

DEC outperforms existing clustering methods on image datasets.

DEC achieves significant improvements on text corpora.

Joint learning of features and clusters enhances clustering quality.

Abstract

Clustering is central to many data-driven application domains and has been studied extensively in terms of distance functions and grouping algorithms. Relatively little work has focused on learning representations for clustering. In this paper, we propose Deep Embedded Clustering (DEC), a method that simultaneously learns feature representations and cluster assignments using deep neural networks. DEC learns a mapping from the data space to a lower-dimensional feature space in which it iteratively optimizes a clustering objective. Our experimental evaluations on image and text corpora show significant improvement over state-of-the-art methods.