An Overview and Evaluation on Graph Neural Networks for Node Classification | ||||
| International Journal of Theoretical and Applied Research | ||||
| Volume 3, Issue 1, June 2024, Page 379-386 PDF (294.25 K) | ||||
| Document Type: Original Article | ||||
| DOI: 10.21608/ijtar.2024.219355.1068 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
asmaa mahmoud mahmoud   1; Abeer S .Desuky 2; heba fathy3; hoda abdeldaim4
| ||||
| 1associate teacher | ||||
| 2proff | ||||
| 3associate professor | ||||
| 4prof | ||||
| Abstract | ||||
| Convolutional and recurrent neural networks, used in computer vision and natural language processing, respectively, have been shown to be effective at improving a variety of machine learning tasks. However, all of the inputs used by these deep learning paradigms are of the Euclidean structure type, such as text or images. Since graphs are a typical non-Euclidean structure in the machine learning area, it is challenging to directly apply these neural networks to graph-based applications like node classification. Due to increased research focus, graph neural networks—which are created to handle specific graph-based input—have made significant advancements. In this article, we present an in-depth review of the use of graph neural networks for the node classification task. The state-of-the-art techniques are first described and broken down into three primary groups: attention technique, convolutional technique, and autoencoder technique. The performance of several approaches is then compared in-depth comparative tests on a number of benchmark datasets. | ||||
| Keywords | ||||
| Graph Neural Network; Node Classification; Graph Convolutional Network; Graph Attention Network | ||||
|
Statistics Article View: 198 PDF Download: 247 |
||||
