Deep $k$-Means: Jointly clustering with $k$-Means and learning representations

TL;DR

This paper introduces Deep $k$-Means, a joint approach that simultaneously learns data representations and performs $k$-Means clustering, resulting in improved clustering performance through a continuous reparametrization of the objective.

Contribution

It proposes a novel joint clustering and representation learning method for $k$-Means based on a continuous reparametrization of the objective function.

Findings

Effective in learning representations while clustering objects.

Demonstrates improved clustering performance on various datasets.

Shows the approach's efficacy through empirical results.

Abstract

We study in this paper the problem of jointly clustering and learning representations. As several previous studies have shown, learning representations that are both faithful to the data to be clustered and adapted to the clustering algorithm can lead to better clustering performance, all the more so that the two tasks are performed jointly. We propose here such an approach for $k$-Means clustering based on a continuous reparametrization of the objective function that leads to a truly joint solution. The behavior of our approach is illustrated on various datasets showing its efficacy in learning representations for objects while clustering them.