MPCC: Matching Priors and Conditionals for Clustering

TL;DR

MPCC is a GAN-based deep generative model with an encoder and flexible decoder that achieves state-of-the-art clustering performance by learning informative data representations and improving sample quality.

Contribution

Introduces MPCC, a novel GAN-based model with learnable priors and an encoder for superior clustering and sample generation.

Findings

Achieves an inception score of 9.49 on CIFAR10.

Improves Fréchet Inception Distance by 46.9% over previous methods.

Outperforms state-of-the-art clustering benchmarks.

Abstract

Clustering is a fundamental task in unsupervised learning that depends heavily on the data representation that is used. Deep generative models have appeared as a promising tool to learn informative low-dimensional data representations. We propose Matching Priors and Conditionals for Clustering (MPCC), a GAN-based model with an encoder to infer latent variables and cluster categories from data, and a flexible decoder to generate samples from a conditional latent space. With MPCC we demonstrate that a deep generative model can be competitive/superior against discriminative methods in clustering tasks surpassing the state of the art over a diverse set of benchmark datasets. Our experiments show that adding a learnable prior and augmenting the number of encoder updates improve the quality of the generated samples, obtaining an inception score of 9.49 $\pm$ 0.15 and improving the Fr\'echet inception distance over the state of the art by a 46.9% in CIFAR10.