Learning a mixture of graph neural networks

GNN models are designed to handle complex and non-uniform graph-structured data for classification tasks such as node, link, and graph-level predictions. However, the randomness and unfixed node ordering of graph data still proposes a challenge to GNN models. To improve the accuracy of GNN mod...

Full description

Saved in:

Bibliographic Details
Main Author:	Lai, Yu-Shiang
Other Authors:	Tay Wee Peng
Format:	Final Year Project
Language:	English
Published:	Nanyang Technological University 2023
Subjects:	Engineering::Electrical and electronic engineering
Online Access:	https://hdl.handle.net/10356/167150
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Nanyang Technological University
Language:	English

id	sg-ntu-dr.10356-167150
record_format	dspace
spelling	sg-ntu-dr.10356-1671502023-07-07T18:06:47Z Learning a mixture of graph neural networks Lai, Yu-Shiang Tay Wee Peng School of Electrical and Electronic Engineering wptay@ntu.edu.sg Engineering::Electrical and electronic engineering GNN models are designed to handle complex and non-uniform graph-structured data for classification tasks such as node, link, and graph-level predictions. However, the randomness and unfixed node ordering of graph data still proposes a challenge to GNN models. To improve the accuracy of GNN models, this study proposes a mixture model approach that combines multiple renowned GNN architectures to produce a single output. The study discusses the advantages of several GNN architectures and tests the models on selected benchmark datasets to examine their validity. By comparing simple GNN models to mixture models, the study hopes to provide insights into the development of more accurate GNN models. Bachelor of Engineering (Electrical and Electronic Engineering) 2023-05-23T11:56:50Z 2023-05-23T11:56:50Z 2023 Final Year Project (FYP) Lai, Y. (2023). Learning a mixture of graph neural networks. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/167150 https://hdl.handle.net/10356/167150 en A3016-221 application/pdf Nanyang Technological University
institution	Nanyang Technological University
building	NTU Library
continent	Asia
country	Singapore Singapore
content_provider	NTU Library
collection	DR-NTU
language	English
topic	Engineering::Electrical and electronic engineering
spellingShingle	Engineering::Electrical and electronic engineering Lai, Yu-Shiang Learning a mixture of graph neural networks
description	GNN models are designed to handle complex and non-uniform graph-structured data for classification tasks such as node, link, and graph-level predictions. However, the randomness and unfixed node ordering of graph data still proposes a challenge to GNN models. To improve the accuracy of GNN models, this study proposes a mixture model approach that combines multiple renowned GNN architectures to produce a single output. The study discusses the advantages of several GNN architectures and tests the models on selected benchmark datasets to examine their validity. By comparing simple GNN models to mixture models, the study hopes to provide insights into the development of more accurate GNN models.
author2	Tay Wee Peng
author_facet	Tay Wee Peng Lai, Yu-Shiang
format	Final Year Project
author	Lai, Yu-Shiang
author_sort	Lai, Yu-Shiang
title	Learning a mixture of graph neural networks
title_short	Learning a mixture of graph neural networks
title_full	Learning a mixture of graph neural networks
title_fullStr	Learning a mixture of graph neural networks
title_full_unstemmed	Learning a mixture of graph neural networks
title_sort	learning a mixture of graph neural networks
publisher	Nanyang Technological University
publishDate	2023
url	https://hdl.handle.net/10356/167150
_version_	1772826435154608128

Learning a mixture of graph neural networks

Similar Items