Approaching feature matrix: To solve two issues in link prediction
- Authors
- Choi, Yeojun; Cho, Yoon-Sik
- Issue Date
- Dec-2023
- Publisher
- PERGAMON-ELSEVIER SCIENCE LTD
- Keywords
- Link prediction; Graph embedding; Isolated node; Random negative sampling
- Citation
- EXPERT SYSTEMS WITH APPLICATIONS, v.234
- Journal Title
- EXPERT SYSTEMS WITH APPLICATIONS
- Volume
- 234
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/69982
- DOI
- 10.1016/j.eswa.2023.120985
- ISSN
- 0957-4174
1873-6793
- Abstract
- With the increase of graph-structure data, link prediction has become an active research topic. Recent progress in link prediction involves learning graph embeddings through graph neural networks. Graph autoencoders(GAE), variational graph autoencoders(VGAE), and their variants such as graph normalized autoencoders(GNAE) try to learn graph embeddings in an unsupervised setting and show promising results in link prediction. However, they suffer from degraded performance with two issues; they tend to assign close to-zero embedding on nodes with zero degree (i.e., isolated node problem) and the issue caused by random negative sampling has not been addressed in link prediction experiments. As the two issues affect only links and not feature information, we propose a generic learning method based on the property of feature information that alleviates both issues and outperforms strong baselines across benchmark datasets.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Software > Department of Artificial Intelligence > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.