# From Logits to Hierarchies: Hierarchical Clustering made Simple

arXiv: https://arxiv.org/abs/2410.07858 · HTML: https://mlsanity.com/paper/2410.07858/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 54 references that are in the map.
- First posted on arXiv 10 Oct 2024.

## Builds on (most cited first, 22 of 22)

- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [Hyperbolic Graph Neural Networks](https://mlsanity.com/paper/1910.12892/) (2019)
- [Hyperbolic Image Embeddings](https://mlsanity.com/paper/1904.02239/) (2019)
- [Benchmarking Representation Learning for Natural World Image Collections](https://mlsanity.com/paper/2103.16483/) (2021)
- [Making Better Mistakes: Leveraging Class Hierarchies with Deep Networks](https://mlsanity.com/paper/1912.09393/) (2019)
- [From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clustering](https://mlsanity.com/paper/2010.00402/) (2020)
- [Adaptive Neural Trees](https://mlsanity.com/paper/1807.06699/) (2018)
- [A cost function for similarity-based hierarchical clustering](https://mlsanity.com/paper/1510.05043/) (2015)
- [Hierarchical Clustering: Objective Functions and Algorithms](https://mlsanity.com/paper/1704.02147/) (2017)
- [Twin Contrastive Learning for Online Clustering](https://mlsanity.com/paper/2210.11680/) (2022)
- [Interpretability and Explainability: A Machine Learning Zoo Mini-tour](https://mlsanity.com/paper/2012.01805/) (2020)
- [Exploring the Limits of Deep Image Clustering using Pretrained Models](https://mlsanity.com/paper/2303.17896/) (2023)
- [Nonparametric Variational Auto-encoders for Hierarchical Representation Learning](https://mlsanity.com/paper/1703.07027/) (2017)
- [No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks](https://mlsanity.com/paper/2104.00795/) (2021)
- [Let Go of Your Labels with Unsupervised Transfer](https://mlsanity.com/paper/2406.07236/) (2024)
- [Fine-grain Inference on Out-of-Distribution Data with Hierarchical Classification](https://mlsanity.com/paper/2209.04493/) (2022)
- [Tree Variational Autoencoders](https://mlsanity.com/paper/2306.08984/) (2023)
- [Hierarchical Selective Classification](https://mlsanity.com/paper/2405.11533/) (2024)
- [Hierarchically Clustered Representation Learning](https://mlsanity.com/paper/1901.09906/) (2019)
- [An Empirical Study into Clustering of Unseen Datasets with Self-Supervised Encoders](https://mlsanity.com/paper/2406.02465/) (2024)
- [The LORACs prior for VAEs: Letting the Trees Speak for the Data](https://mlsanity.com/paper/1810.06891/) (2018)
- [scTree: Discovering Cellular Hierarchies in the Presence of Batch Effects in scRNA-seq Data](https://mlsanity.com/paper/2406.19300/) (2024)

## Built on by (most cited first, 3 of 3)

- [Emergence of Hierarchical Emotion Organization in Large Language Models](https://mlsanity.com/paper/2507.10599/) (2025)
- [Deep Taxonomic Networks for Unsupervised Hierarchical Prototype Discovery](https://mlsanity.com/paper/2509.23602/) (2025)
- [Tree-Structured Orthonormal Decomposition of the Aitchison Simplex](https://mlsanity.com/paper/2606.11646/) (2026)

## Abstract (arXiv)

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.