Variational Graph Convolutional Neural Networks

TL;DR

This paper introduces Variational Graph Convolutional Neural Networks that estimate uncertainty in outputs and attentions, enhancing explainability and accuracy in social trading and human action recognition tasks.

Contribution

It presents novel variational versions of spatial and spatio-temporal GCNs that incorporate uncertainty estimation for improved interpretability and performance.

Findings

Improved model accuracy in social trading and action recognition tasks.

Effective uncertainty estimation enhances model explainability.

Demonstrated benefits across multiple datasets.

Abstract

Estimation of model uncertainty can help improve the explainability of Graph Convolutional Networks and the accuracy of the models at the same time. Uncertainty can also be used in critical applications to verify the results of the model by an expert or additional models. In this paper, we propose Variational Neural Network versions of spatial and spatio-temporal Graph Convolutional Networks. We estimate uncertainty in both outputs and layer-wise attentions of the models, which has the potential for improving model explainability. We showcase the benefits of these models in the social trading analysis and the skeleton-based human action recognition tasks on the Finnish board membership, NTU-60, NTU-120 and Kinetics datasets, where we show improvement in model accuracy in addition to estimated model uncertainties.