Towards Robust and Scalable Density-based Clustering via Graph Propagation
For practitioners needing robust clustering on large-scale, high-dimensional data, CluProp reduces parameter sensitivity and improves scalability.
CluProp reimagines density-based clustering as label propagation on neighborhood graphs, achieving scalable clustering of millions of points in minutes with superior accuracy compared to existing methods.
We present \textit{CluProp}, a novel framework that reimagines varied-density clustering in high-dimensional spaces as a label propagation process over neighborhood graphs. Our approach formally bridges the gap between density-based clustering and graph connectivity, leveraging efficient propagation mechanisms from network science to mitigate the parameter sensitivity inherent in traditional density-based methods. Specifically, we introduce a deterministic density-based propagation strategy to ensure scalable neighborhood identification. The framework is agnostic to the choice of distance metric and exhibits superior performance on large-scale data, processing millions of points in minutes while consistently outperforming existing baselines in accuracy.