Problem
Research questions and friction points this paper is trying to address.
Density Peak Clustering
Clustering Stability
Low-density Regions
Uphill Paths
Local Perturbations
Gradient-Guided Density Peak Clustering
🤖 AI Summary
This study addresses the limitations of density peak clustering, including path instability in low-density regions, assignment sensitivity, and the obscuring of underlying geometric structures. To overcome these issues, this work proposes Gradient-Guided Density Peak Clustering (GGDPC), which introduces a gradient ascent mechanism to optimize neighbor search. Furthermore, it establishes a theoretical connection between the GGDPC graph and the global density gradient flow, mathematically guaranteeing clustering stability and geometric interpretability. By integrating density estimation with multi-criteria consensus analysis techniques, the proposed approach is rigorously evaluated against baseline models. Experimental results demonstrate that GGDPC significantly outperforms existing baselines across five evaluation metrics, including local pattern recovery and the Adjusted Rand Index, thereby validating its consistency and overall superiority.
📝 Abstract
Density peak clustering (DPC) connects each observation to its nearest neighbor of higher density and identifies cluster centers as high-density observations with unusually large nearest neighbor uphill shifts. The resulting uphill paths from observations to cluster centers, however, can be irregular and unstable in low-density regions, making the clustering assignments sensitive to local perturbations and obscuring the population geometry of the DPC graph. In this paper, we introduce \emph{gradient-guided density peak clustering} (GGDPC), which performs a gradient ascent step before each nearest neighbor uphill search. We develop a stability theory that relates the GGDPC graph to the gradient ascent flow of the population density. In particular, we establish consistency of GGDPC under five complementary criteria: recovery of local modes, adjusted Rand index, dendrogram (cluster tree), path length, and waterfall measure. Together, these results provide new statistical, geometric, and topological interpretations of DPC-type clustering algorithms.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Density Peak Clustering
Gradient Ascent
Stability Theory
Clustering Consistency
Population Geometry
🔎 Similar Papers
No similar papers found.
