# Deep clustering with concrete k-means

arXiv: https://arxiv.org/abs/1910.08031 · HTML: https://mlsanity.com/paper/1910.08031/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Oct 2019.

## Built on by (most cited first, 11 of 11)

- [A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning](https://mlsanity.com/paper/2110.01515/) (2021)
- [Interpretable Deep Clustering for Tabular Data](https://mlsanity.com/paper/2306.04785/) (2023)
- [Feature Representation Learning for Unsupervised Cross-domain Image Retrieval](https://mlsanity.com/paper/2207.09721/) (2022)
- [Which Pixel to Annotate: a Label-Efficient Nuclei Segmentation Framework](https://mlsanity.com/paper/2212.10305/) (2022)
- [Prototype-based Dataset Comparison](https://mlsanity.com/paper/2309.02401/) (2023)
- [Selective Pseudo-label Clustering](https://mlsanity.com/paper/2107.10692/) (2021)
- [Hard Regularization to Prevent Deep Online Clustering Collapse without Data Augmentation](https://mlsanity.com/paper/2303.16521/) (2023)
- [Towards Unsupervised Sketch-based Image Retrieval](https://mlsanity.com/paper/2105.08237/) (2021)
- [Concrete Dense Network for Long-Sequence Time Series Clustering](https://mlsanity.com/paper/2405.05015/) (2024)
- [K-Means as a Radial Basis function Network: a Variational and Gradient-based Equivalence](https://mlsanity.com/paper/2603.04625/) (2026)
- [Cohort Organized Learning: Clustering Through Agreement](https://mlsanity.com/paper/2606.21743/) (2026)

## Abstract (arXiv)

We address the problem of simultaneously learning a k-means clustering and deep feature representation from unlabelled data, which is of interest due to the potential of deep k-means to outperform traditional two-step feature extraction and shallow-clustering strategies. We achieve this by developing a gradient-estimator for the non-differentiable k-means objective via the Gumbel-Softmax reparameterisation trick. In contrast to previous attempts at deep clustering, our concrete k-means model can be optimised with respect to the canonical k-means objective and is easily trained end-to-end without resorting to alternating optimisation. We demonstrate the efficacy of our method on standard clustering benchmarks.