Federated Learning on Non-IID Graphs via Structural Knowledge Sharing

Tan, Y; Liu, Y; Long, G; Jiang, J; Lu, Q; Zhang, C

Federated Learning on Non-IID Graphs via Structural Knowledge Sharing

Tan, Y Liu, Y Long, G

Jiang, J

Lu, Q Zhang, C

Permalink

Publication Type:: Conference Proceeding
Citation:: Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023, 2023, 37, pp. 9953-9961
Issue Date:: 2023-06-27

Closed Access

	Filename	Description	Size
	2211.13009_OPUS.pdf	Accepted version	3.19 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Tan, Y
dc.contributor.author	Liu, Y
dc.contributor.author	Long, G https://orcid.org/0000-0003-3740-9515
dc.contributor.author	Jiang, J https://orcid.org/0000-0001-5301-7779
dc.contributor.author	Lu, Q
dc.contributor.author	Zhang, C https://orcid.org/0000-0001-5715-7154
dc.date.accessioned	2024-03-13T00:12:56Z
dc.date.available	2024-03-13T00:12:56Z
dc.date.issued	2023-06-27
dc.identifier.citation	Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023, 2023, 37, pp. 9953-9961
dc.identifier.isbn	9781577358800
dc.identifier.uri	http://hdl.handle.net/10453/176601
dc.description.abstract	Graph neural networks (GNNs) have shown their superiority in modeling graph data. Owing to the advantages of federated learning, federated graph learning (FGL) enables clients to train strong GNN models in a distributed manner without sharing their private data. A core challenge in federated systems is the non-IID problem, which also widely exists in real-world graph data. For example, local data of clients may come from diverse datasets or even domains, e.g., social networks and molecules, increasing the difficulty for FGL methods to capture commonly shared knowledge and learn a generalized encoder. From real-world graph datasets, we observe that some structural properties are shared by various domains, presenting great potential for sharing structural knowledge in FGL. Inspired by this, we propose FedStar, an FGL framework that extracts and shares the common underlying structure information for inter-graph federated learning tasks. To explicitly extract the structure information rather than encoding them along with the node features, we define structure embeddings and encode them with an independent structure encoder. Then, the structure encoder is shared across clients while the feature-based knowledge is learned in a personalized way, making FedStar capable of capturing more structure-based domain-invariant information and avoiding feature misalignment issues. We perform extensive experiments over both cross-dataset and cross-domain non-IID FGL settings, demonstrating the superiority of FedStar.
dc.language	en
dc.relation.ispartof	Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Federated Learning on Non-IID Graphs via Structural Knowledge Sharing
dc.type	Conference Proceeding
utslib.citation.volume	37
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/DVC (International)
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Strength - ACRI - Australia China Relations Institute
pubs.organisational-group	University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
utslib.copyright.status	closed_access	*
dc.date.updated	2024-03-13T00:12:50Z
pubs.publication-status	Published
pubs.volume	37

Abstract:

Graph neural networks (GNNs) have shown their superiority in modeling graph data. Owing to the advantages of federated learning, federated graph learning (FGL) enables clients to train strong GNN models in a distributed manner without sharing their private data. A core challenge in federated systems is the non-IID problem, which also widely exists in real-world graph data. For example, local data of clients may come from diverse datasets or even domains, e.g., social networks and molecules, increasing the difficulty for FGL methods to capture commonly shared knowledge and learn a generalized encoder. From real-world graph datasets, we observe that some structural properties are shared by various domains, presenting great potential for sharing structural knowledge in FGL. Inspired by this, we propose FedStar, an FGL framework that extracts and shares the common underlying structure information for inter-graph federated learning tasks. To explicitly extract the structure information rather than encoding them along with the node features, we define structure embeddings and encode them with an independent structure encoder. Then, the structure encoder is shared across clients while the feature-based knowledge is learned in a personalized way, making FedStar capable of capturing more structure-based domain-invariant information and avoiding feature misalignment issues. We perform extensive experiments over both cross-dataset and cross-domain non-IID FGL settings, demonstrating the superiority of FedStar.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/176601