# Hierarchically Clustered Representation Learning

arXiv: https://arxiv.org/abs/1901.09906 · HTML: https://mlsanity.com/paper/1901.09906/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jan 2019.

## Built on by (most cited first, 6 of 6)

- [Unsupervised Representation Learning for Time Series: A Review](https://mlsanity.com/paper/2308.01578/) (2023)
- [Tree Variational Autoencoders](https://mlsanity.com/paper/2306.08984/) (2023)
- [Deep Taxonomic Networks for Unsupervised Hierarchical Prototype Discovery](https://mlsanity.com/paper/2509.23602/) (2025)
- [From Logits to Hierarchies: Hierarchical Clustering made Simple](https://mlsanity.com/paper/2410.07858/) (2024)
- [scTree: Discovering Cellular Hierarchies in the Presence of Batch Effects in scRNA-seq Data](https://mlsanity.com/paper/2406.19300/) (2024)
- [Simple and Scalable Algorithms for Cluster-Aware Precision Medicine](https://mlsanity.com/paper/2211.16553/) (2022)

## Abstract (arXiv)

The joint optimization of representation learning and clustering in the embedding space has experienced a breakthrough in recent years. In spite of the advance, clustering with representation learning has been limited to flat-level categories, which often involves cohesive clustering with a focus on instance relations. To overcome the limitations of flat clustering, we introduce hierarchically-clustered representation learning (HCRL), which simultaneously optimizes representation learning and hierarchical clustering in the embedding space. Compared with a few prior works, HCRL firstly attempts to consider a generation of deep embeddings from every component of the hierarchy, not just leaf components. In addition to obtaining hierarchically clustered embeddings, we can reconstruct data by the various abstraction levels, infer the intrinsic hierarchical structure, and learn the level-proportion features. We conducted evaluations with image and text domains, and our quantitative analyses showed competent likelihoods and the best accuracies compared with the baselines.