English

Deep Amortized Clustering

Machine Learning 2019-10-01 v1 Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.1909.13433,
  title  = {Deep Amortized Clustering},
  author = {Juho Lee and Yoonho Lee and Yee Whye Teh},
  journal= {arXiv preprint arXiv:1909.13433},
  year   = {2019}
}
R2 v1 2026-06-23T11:29:43.906Z