Variational graph autoencoders for multiview canonical correlation analysis

We present a novel approach for multiview canonical correlation analysis based on a variational graph neural network model. We propose a nonlinear model which takes into account the available graph based geometric constraints while being scalable to large-scale datasets with multiple views. This model combines the probabilistic interpretation of CCA with an autoencoder architecture based on graph convolutional neural network layers. Experiments with the proposed method are conducted on classification, clustering, and recommendation tasks on real datasets. The algorithm is competitive with state-of-the-art multiview representation learning techniques, in addition to being scalable and robust to instances with missing views. (c) 2021 Elsevier B.V. All rights reserved.

Automated summary

This paper presents a novel approach for multiview canonical correlation analysis based on a variational graph neural network model, which combines the probabilistic interpretation of CCA with an autoencoder architecture based on graph convolutional neural network layers. Experimental results show that the proposed method performs well on classification, clustering, and recommendation tasks, and is competitive with state-of-the-art multiview representation learning techniques, while maintaining scalability and robustness to instances with missing views.