Social Influence Prediction with Train and Test Time Augmentation for Graph Neural Networks

TL;DR

This paper introduces a novel train- and test-time augmentation method for graph neural networks to improve social influence prediction, especially on smaller social network graphs, by leveraging a variational graph autoencoder.

Contribution

It proposes a new augmentation technique using a variational graph autoencoder at both train and test stages for social influence prediction with GNNs.

Findings

Outperforms state-of-the-art methods on multiple social network datasets.

More effective on smaller graphs.

End-to-end training of autoencoder and influence classifier improves accuracy.

Abstract

Data augmentation has been widely used in machine learning for natural language processing and computer vision tasks to improve model performance. However, little research has studied data augmentation on graph neural networks, particularly using augmentation at both train- and test-time. Inspired by the success of augmentation in other domains, we have designed a method for social influence prediction using graph neural networks with train- and test-time augmentation, which can effectively generate multiple augmented graphs for social networks by utilising a variational graph autoencoder in both scenarios. We have evaluated the performance of our method on predicting user influence on multiple social network datasets. Our experimental results show that our end-to-end approach, which jointly trains a graph autoencoder and social influence behaviour classification network, can outperform state-of-the-art approaches, demonstrating the effectiveness of train- and test-time augmentation on graph neural networks for social influence prediction. We observe that this is particularly effective on smaller graphs.