Buchumschlag

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

Gespeichert in:
Veröffentlicht in:arXiv.org (Apr 23, 2021), p. n/a
1. Verfasser: Bo, Hongbo
Weitere Verfasser: McConville, Ryan, Hong, Jun, Liu, Weiru
Veröffentlicht:
Cornell University Library, arXiv.org
Schlagworte:
Testing time
Computer vision
Performance evaluation
Graphs
Social networks
Machine learning
Natural language processing
Neural networks
Graph neural networks
Data augmentation
Online-Zugang:Citation/Abstract
Full text outside of ProQuest
Tags: Tag hinzufügen
Keine Tags, Fügen Sie das erste Tag hinzu!
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.
ISSN:2331-8422
Quelle:Engineering Database