Neural Clustering By Predicting And Copying Noise

Sam Coope, Andrej Zukov-Gregoric, Yoram Bachrach

Abstract: We propose a neural clustering model that jointly learns both latent features and how they cluster. Unlike similar methods our model does not require a predefined number of clusters. Using a supervised approach, we agglomerate latent features towards randomly sampled targets within the same space whilst progressively removing the targets until we are left with only targets which represent cluster centroids. To show the behavior of our model across different modalities we apply our model on both text and image data and very competitive results on MNIST. Finally, we also provide results against baseline models for fashion-MNIST, the 20 newsgroups dataset, and a Twitter dataset we ourselves create.

TL;DR: Neural clustering without needing a number of clusters

Keywords: unsupervised learning, clustering, deep learning

Data: [Fashion-MNIST](https://paperswithcode.com/dataset/fashion-mnist), [MNIST](https://paperswithcode.com/dataset/mnist)