From Logits to Hierarchies: Hierarchical Clustering made Simple

TL;DR

This paper introduces a simple, scalable hierarchical clustering method built on pre-trained non-hierarchical models, outperforming complex deep models and applicable in supervised settings without fine-tuning.

Contribution

The paper presents a lightweight hierarchical clustering approach that leverages pre-trained logits, offering a practical alternative to complex deep hierarchical models with broad applicability.

Findings

Outperforms deep hierarchical clustering models in scalability and performance.

Applicable to pre-trained models without fine-tuning.

Effective in both unsupervised and supervised hierarchical tasks.

Abstract

The hierarchical structure inherent in many real-world datasets makes the modeling of such hierarchies a crucial objective in both unsupervised and supervised machine learning. While recent advancements have introduced deep architectures specifically designed for hierarchical clustering, we adopt a critical perspective on this line of research. Our findings reveal that these methods face significant limitations in scalability and performance when applied to realistic datasets. Given these findings, we present an alternative approach and introduce a lightweight method that builds on pre-trained non-hierarchical clustering models. Remarkably, our approach outperforms specialized deep models for hierarchical clustering, and it is broadly applicable to any pre-trained clustering model that outputs logits, without requiring any fine-tuning. To highlight the generality of our approach, we extend its application to a supervised setting, demonstrating its ability to recover meaningful hierarchies from a pre-trained ImageNet classifier. Our results establish a practical and effective alternative to existing deep hierarchical clustering methods, with significant advantages in efficiency, scalability and performance.