# Deep Amortized Clustering

arXiv: https://arxiv.org/abs/1909.13433 · HTML: https://mlsanity.com/paper/1909.13433/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2019.

## Built on by (most cited first, 9 of 9)

- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [You Never Cluster Alone](https://mlsanity.com/paper/2106.01908/) (2021)
- [Amortized Variational Inference: A Systematic Review](https://mlsanity.com/paper/2209.10888/) (2022)
- [Measuring the Interpretability of Unsupervised Representations via Quantized Reverse Probing](https://mlsanity.com/paper/2209.03268/) (2022)
- [TabClustPFN: A Prior-data Fitted Network for Tabular Data Clustering](https://mlsanity.com/paper/2601.21656/) (2026)
- [PICASO: Permutation-Invariant Cascaded Attentional Set Operator](https://mlsanity.com/paper/2107.08305/) (2021)
- [Advances in Set Function Learning: A Survey of Techniques and Applications](https://mlsanity.com/paper/2501.14991/) (2025)
- [Consistent Amortized Clustering via Generative Flow Networks](https://mlsanity.com/paper/2502.19337/) (2025)
- [Enhancing Video Understanding: Deep Neural Networks for Spatiotemporal Analysis](https://mlsanity.com/paper/2502.07277/) (2025)

## Abstract (arXiv)

We propose a deep amortized clustering (DAC), a neural architecture which learns to cluster datasets efficiently using a few forward passes. DAC implicitly learns what makes a cluster, how to group data points into clusters, and how to count the number of clusters in datasets. DAC is meta-learned using labelled datasets for training, a process distinct from traditional clustering algorithms which usually require hand-specified prior knowledge about cluster shapes/structures. We empirically show, on both synthetic and image data, that DAC can efficiently and accurately cluster new datasets coming from the same distribution used to generate training datasets.