Poster
Learning Latent Superstructures in Variational Autoencoders for Deep Multidimensional Clustering
Xiaopeng Li · Zhourong Chen · Leonard Poon · Nevin Zhang
Great Hall BC #83
Keywords: [ multidimensional clustering ] [ message passing ] [ stepwise em ] [ structure learning ] [ bayesian network ] [ latent variable model ] [ latent tree model ] [ graphical model ] [ variational autoencoder ] [ deep learning ] [ unsupervised learning ]
We investigate a variant of variational autoencoders where there is a superstructure of discrete latent variables on top of the latent features. In general, our superstructure is a tree structure of multiple super latent variables and it is automatically learned from data. When there is only one latent variable in the superstructure, our model reduces to one that assumes the latent features to be generated from a Gaussian mixture model. We call our model the latent tree variational autoencoder (LTVAE). Whereas previous deep learning methods for clustering produce only one partition of data, LTVAE produces multiple partitions of data, each being given by one super latent variable. This is desirable because high dimensional data usually have many different natural facets and can be meaningfully partitioned in multiple ways.
Live content is unavailable. Log in and register to view live content