Clustering Based on Density Propagation and Subcluster Merging

TL;DR

The paper introduces DPSM, a density propagation-based clustering method that automatically determines the number of clusters and effectively merges subclusters, applicable in both data and graph spaces.

Contribution

It presents a novel density propagation approach for clustering that eliminates the need for distance calculations and extends spectral clustering to small clusters with a new merging criterion.

Findings

DPSM accurately identifies clusters in various datasets.

The method effectively merges subclusters using the CluCut measure.

Experiments demonstrate superior performance over traditional methods.

Abstract

We propose the DPSM method, a density-based node clustering approach that automatically determines the number of clusters and can be applied in both data space and graph space. Unlike traditional density-based clustering methods, which necessitate calculating the distance between any two nodes, our proposed technique determines density through a propagation process, thereby making it suitable for a graph space. In DPSM, nodes are partitioned into small clusters based on propagated density. The partitioning technique has been proved to be sound and complete. We then extend the concept of spectral clustering from individual nodes to these small clusters, while introducing the CluCut measure to guide cluster merging. This measure is modified in various ways to account for cluster properties, thus provides guidance on when to terminate the merging process. Various experiments have validated the effectiveness of DOSM and the accuracy of these conclusions.