Multiview Variational Graph Autoencoders for Canonical Correlation Analysis

TL;DR

This paper introduces a scalable, nonlinear multiview canonical correlation analysis model using variational autoencoders and graph convolutional networks, effectively handling large datasets with geometric constraints.

Contribution

It presents the first nonlinear multiview CCA model that incorporates graph-based geometric constraints and is scalable for large datasets.

Findings

Competitive performance on classification tasks

Effective in clustering applications

Suitable for recommendation systems

Abstract

We present a novel multiview canonical correlation analysis model based on a variational approach. This is the first nonlinear model that takes into account the available graph-based geometric constraints while being scalable for processing large scale datasets with multiple views. It is based on an autoencoder architecture with graph convolutional neural network layers. We experiment with our approach on classification, clustering, and recommendation tasks on real datasets. The algorithm is competitive with state-of-the-art multiview representation learning techniques.