Federated learning for graph neural networks

This dissertation investigates the combination of graph neural networks (GNNs) and federated learning (FL) for addressing practical problems while preserving data privacy and reducing computational complexity. Specifically, we reproduce the Graph Clustered Federated Learning (GCFL) framework and...

Full description

Saved in:

Bibliographic Details
Main Author:	Yan, Yige
Other Authors:	Tay Wee Peng
Format:	Thesis-Master by Coursework
Language:	English
Published:	Nanyang Technological University 2023
Subjects:	Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Online Access:	https://hdl.handle.net/10356/167083
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Nanyang Technological University
Language:	English

id	sg-ntu-dr.10356-167083
record_format	dspace
spelling	sg-ntu-dr.10356-1670832023-07-04T16:43:36Z Federated learning for graph neural networks Yan, Yige Tay Wee Peng School of Electrical and Electronic Engineering wptay@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence This dissertation investigates the combination of graph neural networks (GNNs) and federated learning (FL) for addressing practical problems while preserving data privacy and reducing computational complexity. Specifically, we reproduce the Graph Clustered Federated Learning (GCFL) framework and proposed the Privacy Preserving Graph Clustered Federated Learning (PP-GCFL) algorithm, which enhance model performance and privacy protection. Master of Science (Computer Control and Automation) 2023-05-15T06:35:04Z 2023-05-15T06:35:04Z 2023 Thesis-Master by Coursework Yan, Y. (2023). Federated learning for graph neural networks. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/167083 https://hdl.handle.net/10356/167083 en 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::Computer science and engineering::Computing methodologies::Artificial intelligence
spellingShingle	Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Yan, Yige Federated learning for graph neural networks
description	This dissertation investigates the combination of graph neural networks (GNNs) and federated learning (FL) for addressing practical problems while preserving data privacy and reducing computational complexity. Specifically, we reproduce the Graph Clustered Federated Learning (GCFL) framework and proposed the Privacy Preserving Graph Clustered Federated Learning (PP-GCFL) algorithm, which enhance model performance and privacy protection.
author2	Tay Wee Peng
author_facet	Tay Wee Peng Yan, Yige
format	Thesis-Master by Coursework
author	Yan, Yige
author_sort	Yan, Yige
title	Federated learning for graph neural networks
title_short	Federated learning for graph neural networks
title_full	Federated learning for graph neural networks
title_fullStr	Federated learning for graph neural networks
title_full_unstemmed	Federated learning for graph neural networks
title_sort	federated learning for graph neural networks
publisher	Nanyang Technological University
publishDate	2023
url	https://hdl.handle.net/10356/167083
_version_	1772828156663693312

Federated learning for graph neural networks

Similar Items