Deep Clustering with Associative Memories

TL;DR

This paper introduces DCAM, a novel deep clustering method that integrates representation learning and clustering through an energy-based loss function using Associative Memories, improving clustering quality across various architectures and data types.

Contribution

The paper presents a new loss function based on energy dynamics with Associative Memories, unifying representation learning and clustering in deep learning.

Findings

DCAM improves clustering quality across architectures.

Effective on image and text data.

Compatible with various neural network types.

Abstract

Deep clustering - joint representation learning and latent space clustering - is a well studied problem especially in computer vision and text processing under the deep learning framework. While the representation learning is generally differentiable, clustering is an inherently discrete optimization task, requiring various approximations and regularizations to fit in a standard differentiable pipeline. This leads to a somewhat disjointed representation learning and clustering. In this work, we propose a novel loss function utilizing energy-based dynamics via Associative Memories to formulate a new deep clustering method, DCAM, which ties together the representation learning and clustering aspects more intricately in a single objective. Our experiments showcase the advantage of DCAM, producing improved clustering quality for various architecture choices (convolutional, residual or fully-connected) and data modalities (images or text).