Multi-Facet Clustering Variational Autoencoders
This addresses the limitation of deep clustering focusing on single partitions, enabling multi-faceted analysis for domains like image processing, though it appears incremental as it builds on variational autoencoders.
The paper tackles the problem of learning multiple clusterings simultaneously from high-dimensional data like images, introducing Multi-Facet Clustering Variational Autoencoders (MFCVAE) that separate and cluster different aspects of data in a disentangled manner, with demonstrated advantages in compositionality and controlled generation.
Work in deep clustering focuses on finding a single partition of data. However, high-dimensional data, such as images, typically feature multiple interesting characteristics one could cluster over. For example, images of objects against a background could be clustered over the shape of the object and separately by the colour of the background. In this paper, we introduce Multi-Facet Clustering Variational Autoencoders (MFCVAE), a novel class of variational autoencoders with a hierarchy of latent variables, each with a Mixture-of-Gaussians prior, that learns multiple clusterings simultaneously, and is trained fully unsupervised and end-to-end. MFCVAE uses a progressively-trained ladder architecture which leads to highly stable performance. We provide novel theoretical results for optimising the ELBO analytically with respect to the categorical variational posterior distribution, correcting earlier influential theoretical work. On image benchmarks, we demonstrate that our approach separates out and clusters over different aspects of the data in a disentangled manner. We also show other advantages of our model: the compositionality of its latent space and that it provides controlled generation of samples.