Graph Neural Networks for Link Prediction
Graph Neural Networks (GNNs) belong to a class of deep learning methods that are specialized for extracting critical information and making accurate predictions on graph representations. Researchers have been striving to adapt neural networks to process graph data for over a decade. GNNs have found...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
LibraryPress@UF
2023-05-01
|
| Series: | Proceedings of the International Florida Artificial Intelligence Research Society Conference |
| Subjects: | |
| Online Access: | https://journals.flvc.org/FLAIRS/article/view/133375 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Graph Neural Networks (GNNs) belong to a class of deep learning methods that are specialized for extracting critical information and making accurate predictions on graph representations. Researchers have been striving to adapt neural networks to process graph data for over a decade. GNNs have found practical applications in various fields, including physics simulations, object detection, and recommendation systems. Predicting missing links in graphs is a crucial problem in various scientific fields because real-world graphs are frequently incompletely observed. This task, also known as link prediction, aims to predict the existence or absence of links in a graph. This tutorial is designed for researchers who have no prior experience with GNNs and will provide an overview of the link prediction task. In addition, we will discuss further reading, applications, and the most commonly used software packages and frameworks. |
|---|---|
| ISSN: | 2334-0754 2334-0762 |