A study on graph neural networks
This report investigates various Graph Neural Network (GNN) models and its performance and stability. GNNs have gained popularity in recent years because they are able to handle graph data structures, which are a common way to represent complex relationships between entities in many real-world appli...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
Nanyang Technological University
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/167731 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | This report investigates various Graph Neural Network (GNN) models and its performance and stability. GNNs have gained popularity in recent years because they are able to handle graph data structures, which are a common way to represent complex relationships between entities in many real-world applications. This project focuses on node classification problems and is tested on public benchmark datasets. The paper discusses the possible improvement in performance and stability using Bootstrapped Graph Latents (BGRL) and compare it to bootstrapping neural networks. |
|---|