ClusterGAN : Latent Space Clustering in Generative Adversarial Networks
This addresses the unsupervised learning problem of clustering for researchers and practitioners, offering a novel method but is incremental as it builds on existing GAN frameworks.
The paper tackles the problem of clustering in GANs by proposing ClusterGAN, which uses a mixture of one-hot encoded and continuous latent variables with an inverse network and clustering-specific loss to achieve clustering in the latent space, showing superior performance compared to baselines on synthetic and real datasets.
Generative Adversarial networks (GANs) have obtained remarkable success in many unsupervised learning tasks and unarguably, clustering is an important unsupervised learning problem. While one can potentially exploit the latent-space back-projection in GANs to cluster, we demonstrate that the cluster structure is not retained in the GAN latent space. In this paper, we propose ClusterGAN as a new mechanism for clustering using GANs. By sampling latent variables from a mixture of one-hot encoded variables and continuous latent variables, coupled with an inverse network (which projects the data to the latent space) trained jointly with a clustering specific loss, we are able to achieve clustering in the latent space. Our results show a remarkable phenomenon that GANs can preserve latent space interpolation across categories, even though the discriminator is never exposed to such vectors. We compare our results with various clustering baselines and demonstrate superior performance on both synthetic and real datasets.