Deep Clustering via Distribution Learning

TL;DR

This paper introduces a theoretically guided deep clustering method called DCDL, which incorporates a novel distribution learning approach, Monte-Carlo Marginalization, to improve clustering performance on standard datasets.

Contribution

It provides a theoretical analysis linking distribution learning and clustering, and proposes a new distribution learning technique tailored for clustering tasks.

Findings

DCDL outperforms state-of-the-art methods on benchmark datasets.

The new distribution learning method improves clustering accuracy.

Theoretical insights guide the optimization of deep clustering.

Abstract

Distribution learning finds probability density functions from a set of data samples, whereas clustering aims to group similar data points to form clusters. Although there are deep clustering methods that employ distribution learning methods, past work still lacks theoretical analysis regarding the relationship between clustering and distribution learning. Thus, in this work, we provide a theoretical analysis to guide the optimization of clustering via distribution learning. To achieve better results, we embed deep clustering guided by a theoretical analysis. Furthermore, the distribution learning method cannot always be directly applied to data. To overcome this issue, we introduce a clustering-oriented distribution learning method called Monte-Carlo Marginalization for Clustering. We integrate Monte-Carlo Marginalization for Clustering into Deep Clustering, resulting in Deep Clustering via Distribution Learning (DCDL). Eventually, the proposed DCDL achieves promising results compared to state-of-the-art methods on popular datasets. Considering a clustering task, the new distribution learning method outperforms previous methods as well.