Deep Variational Canonical Correlation Analysis

TL;DR

Deep variational CCA extends traditional linear CCA to nonlinear models using deep neural networks, enabling better multi-view data analysis and disentanglement of shared and private information.

Contribution

It introduces VCCA and VCCA-private, novel deep models that improve multi-view learning by capturing shared and private features without supervision.

Findings

Competitive performance on real-world datasets

Effective disentanglement of shared and private information

Extension of linear CCA to nonlinear deep models

Abstract

We present deep variational canonical correlation analysis (VCCA), a deep multi-view learning model that extends the latent variable model interpretation of linear CCA to nonlinear observation models parameterized by deep neural networks. We derive variational lower bounds of the data likelihood by parameterizing the posterior probability of the latent variables from the view that is available at test time. We also propose a variant of VCCA called VCCA-private that can, in addition to the "common variables" underlying both views, extract the "private variables" within each view, and disentangles the shared and private information for multi-view data without hard supervision. Experimental results on real-world datasets show that our methods are competitive across domains.