CA-GNN: A Competence-Aware Graph Neural Network for Semi-Supervised Learning on Streaming Data

Yu, H; Wen, J; Sun, Y; Wei, X; Lu, J

CA-GNN: A Competence-Aware Graph Neural Network for Semi-Supervised Learning on Streaming Data

Yu, H Wen, J Sun, Y Wei, X Lu, J

Permalink

Publisher:: Institute of Electrical and Electronics Engineers (IEEE)
Publication Type:: Journal Article
Citation:: IEEE Transactions on Cybernetics, 2024, PP, (99), pp. 1-14
Issue Date:: 2024-01-01

In Progress

	Filename	Description	Size
	1779818.pdf	Published version	5.39 MB		View/Open

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is being processed and is not currently available.

Full metadata record

Field	Value	Language
dc.contributor.author	Yu, H
dc.contributor.author	Wen, J
dc.contributor.author	Sun, Y
dc.contributor.author	Wei, X
dc.contributor.author	Lu, J https://orcid.org/0000-0003-0690-4732
dc.date.accessioned	2025-01-28T09:10:48Z
dc.date.available	2025-01-28T09:10:48Z
dc.date.issued	2024-01-01
dc.identifier.citation	IEEE Transactions on Cybernetics, 2024, PP, (99), pp. 1-14
dc.identifier.issn	2168-2267
dc.identifier.issn	2168-2275
dc.identifier.uri	http://hdl.handle.net/10453/184524
dc.description.abstract	One challenge of learning from streaming data is that only a limited number of labeled examples are available, making semi-supervised learning (SSL) algorithms becoming an efficient tool for streaming data mining. Recently, the graph-based SSL algorithms have been proposed to improve SSL performance because the graph structure can utilize the interactivity between surrounding nodes. However, graph-based SSL algorithms have two main limitations when applied to streaming data. First, not all the labels of the data in the streaming data may be reliable, and direct classification using a graph can lead to suboptimal performance. Second, graph-based SSL algorithms assume the structure of the graph is static, but the learning environment of streaming data is dynamic. Hence, we propose a competence-aware graph neural network (CA-GNN) to deal with these two limitations. Unlike other models, CA-GNN does not directly rely on graph information that could include mislabeled nodes. Instead, a competence model is used to explore latent semantic correlations in the streaming data and capture the reliability for each data. A streaming learning strategy then evolves CA-GNN s parameters to capture the dynamism of the graph sequences. We conducted experiments using seven real datasets and four synthetic datasets, respectively, and compared the outcomes across various methods. The results demonstrate that CA-GNN classifies streaming data more effectively than the state-of-the-art (SOTA) methods.
dc.language	en
dc.publisher	Institute of Electrical and Electronics Engineers (IEEE)
dc.relation.ispartof	IEEE Transactions on Cybernetics
dc.relation.isbasedon	10.1109/tcyb.2024.3489605
dc.rights	info:eu-repo/semantics/restrictedAccess
dc.title	CA-GNN: A Competence-Aware Graph Neural Network for Semi-Supervised Learning on Streaming Data
dc.type	Journal Article
utslib.citation.volume	PP
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/UTS Groups
pubs.organisational-group	University of Technology Sydney/UTS Groups/Australian Artificial Intelligence Institute (AAII)
utslib.copyright.status	in_progress	*
pubs.consider-herdc	true
dc.date.updated	2025-01-28T09:10:44Z
pubs.issue	99
pubs.publication-status	Published
pubs.volume	PP
utslib.citation.issue	99

Abstract:

One challenge of learning from streaming data is that only a limited number of labeled examples are available, making semi-supervised learning (SSL) algorithms becoming an efficient tool for streaming data mining. Recently, the graph-based SSL algorithms have been proposed to improve SSL performance because the graph structure can utilize the interactivity between surrounding nodes. However, graph-based SSL algorithms have two main limitations when applied to streaming data. First, not all the labels of the data in the streaming data may be reliable, and direct classification using a graph can lead to suboptimal performance. Second, graph-based SSL algorithms assume the structure of the graph is static, but the learning environment of streaming data is dynamic. Hence, we propose a competence-aware graph neural network (CA-GNN) to deal with these two limitations. Unlike other models, CA-GNN does not directly rely on graph information that could include mislabeled nodes. Instead, a competence model is used to explore latent semantic correlations in the streaming data and capture the reliability for each data. A streaming learning strategy then evolves CA-GNN s parameters to capture the dynamism of the graph sequences. We conducted experiments using seven real datasets and four synthetic datasets, respectively, and compared the outcomes across various methods. The results demonstrate that CA-GNN classifies streaming data more effectively than the state-of-the-art (SOTA) methods.

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

http://hdl.handle.net/10453/184524