CoHiRF: Hierarchical Consensus for Interpretable Clustering Beyond Scalability Limits

TL;DR

CoHiRF is a hierarchical consensus framework that enhances existing clustering methods by improving robustness, stability, and scalability through multiple low-dimensional views and a multi-resolution, interpretable hierarchy.

Contribution

It introduces a meta-algorithm that applies existing clustering methods repeatedly to create a hierarchical consensus, enabling large-scale, robust, and interpretable clustering without modifying the original methods.

Findings

Improves robustness to high-dimensional noise

Enhances stability under stochastic variability

Enables scalability beyond traditional limits

Abstract

We introduce CoHiRF (Consensus Hierarchical Random Features), a hierarchical consensus framework that enables existing clustering methods to operate beyond their usual computational and memory limits. CoHiRF is a meta-algorithm that operates exclusively on the label assignments produced by a base clustering method, without modifying its objective function, optimization procedure, or geometric assumptions. It repeatedly applies the base method to multiple low-dimensional feature views or stochastic realizations, enforces agreement through consensus, and progressively reduces the problem size via representative-based contraction. Across a diverse set of synthetic and real-world experiments involving centroid-based, kernel-based, density-based, and graph-based methods, we show that CoHiRF can improve robustness to high-dimensional noise, enhance stability under stochastic variability, and enable scalability to regimes where the base method alone is infeasible. We also provide an empirical characterization of when hierarchical consensus is beneficial, highlighting the role of reproducible label relations and their compatibility with representative-based contraction. Beyond flat partitions, CoHiRF produces an explicit Cluster Fusion Hierarchy, offering a multi-resolution and interpretable view of the clustering structure. Together, these results position hierarchical consensus as a practical and flexible tool for large-scale clustering, extending the applicability of existing methods without altering their underlying behavior.