Scalable Varied-Density Clustering via Graph Propagation

TL;DR

This paper introduces a scalable, density-aware graph propagation method for high-dimensional varied-density clustering, combining graph theory and random projections to efficiently handle large datasets with high accuracy.

Contribution

It presents a novel density-adaptive neighborhood propagation algorithm that improves scalability and accuracy in high-dimensional varied-density clustering tasks.

Findings

Scales to datasets with millions of points in minutes.

Achieves competitive accuracy compared to existing methods.

Reduces computational cost significantly.

Abstract

We propose a novel perspective on varied-density clustering for high-dimensional data by framing it as a label propagation process in neighborhood graphs that adapt to local density variations. Our method formally connects density-based clustering with graph connectivity, enabling the use of efficient graph propagation techniques developed in network science. To ensure scalability, we introduce a density-aware neighborhood propagation algorithm and leverage advanced random projection methods to construct approximate neighborhood graphs. Our approach significantly reduces computational cost while preserving clustering quality. Empirically, it scales to datasets with millions of points in minutes and achieves competitive accuracy compared to existing baselines.