Social Influence Prediction with Train and Test Time Augmentation for Graph Neural Networks
Kaydedildi:
| Yayımlandı: | arXiv.org (Apr 23, 2021), p. n/a |
|---|---|
| Yazar: | |
| Diğer Yazarlar: | , , |
| Baskı/Yayın Bilgisi: |
Cornell University Library, arXiv.org
|
| Konular: | |
| Online Erişim: | Citation/Abstract Full text outside of ProQuest |
| Etiketler: |
Etiket eklenmemiş, İlk siz ekleyin!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 2518564423 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2331-8422 | ||
| 035 | |a 2518564423 | ||
| 045 | 0 | |b d20210423 | |
| 100 | 1 | |a Bo, Hongbo | |
| 245 | 1 | |a Social Influence Prediction with Train and Test Time Augmentation for Graph Neural Networks | |
| 260 | |b Cornell University Library, arXiv.org |c Apr 23, 2021 | ||
| 513 | |a Working Paper | ||
| 520 | 3 | |a 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. | |
| 653 | |a Testing time | ||
| 653 | |a Computer vision | ||
| 653 | |a Performance evaluation | ||
| 653 | |a Graphs | ||
| 653 | |a Social networks | ||
| 653 | |a Machine learning | ||
| 653 | |a Natural language processing | ||
| 653 | |a Neural networks | ||
| 653 | |a Graph neural networks | ||
| 653 | |a Data augmentation | ||
| 700 | 1 | |a McConville, Ryan | |
| 700 | 1 | |a Hong, Jun | |
| 700 | 1 | |a Liu, Weiru | |
| 773 | 0 | |t arXiv.org |g (Apr 23, 2021), p. n/a | |
| 786 | 0 | |d ProQuest |t Engineering Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/2518564423/abstract/embedded/ZKJTFFSVAI7CB62C?source=fedsrch |
| 856 | 4 | 0 | |3 Full text outside of ProQuest |u http://arxiv.org/abs/2104.11641 |