Measures of Overlapping Multivariate Gaussian Clusters in Unsupervised Online Learning

TL;DR

This paper introduces a novel, computationally efficient measure for detecting overlaps in multivariate Gaussian clusters within online learning environments, improving cluster merging accuracy in streaming data scenarios.

Contribution

The paper presents a new overlap detection measure tailored for online clustering of Gaussian data, addressing limitations of existing dissimilarity measures in speed and shape sensitivity.

Findings

The proposed measure is several times faster than existing methods.

It effectively detects overlapping clusters without merging orthogonal clusters.

The method improves clustering accuracy in streaming data applications.

Abstract

In this paper, we propose a new measure for detecting overlap in multivariate Gaussian clusters. The aim of online learning from data streams is to create clustering, classification, or regression models that can adapt over time based on the conceptual drift of streaming data. In the case of clustering, this can result in a large number of clusters that may overlap and should be merged. Commonly used distribution dissimilarity measures are not adequate for determining overlapping clusters in the context of online learning from streaming data due to their inability to account for all shapes of clusters and their high computational demands. Our proposed dissimilarity measure is specifically designed to detect overlap rather than dissimilarity and can be computed faster compared to existing measures. Our method is several times faster than compared methods and is capable of detecting overlapping clusters while avoiding the merging of orthogonal clusters.