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.
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}
}