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

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

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.
Original languageEnglish
Title of host publicationInternational Joint Conference on Neural Networks 2021 (IJCNN 2021)
Number of pages8
Publication statusAccepted/In press - 10 Apr 2021
EventThe International Joint Conference on Neural Networks 2021 (IJCNN 2021) -
Duration: 18 Jun 202122 Jun 2021
https://www.ijcnn.org/

Conference

ConferenceThe International Joint Conference on Neural Networks 2021 (IJCNN 2021)
Period18/06/2122/06/21
Internet address

Fingerprint

Dive into the research topics of 'Social Influence Prediction with Train and Test Time Augmentation for Graph Neural Networks'. Together they form a unique fingerprint.

Cite this