GNNBoost: boosting artwork classification with graph embeddings

El Vaigh, Cheikh Brahim; Garcia, Noa; Renoust, Benjamin; Chu, Chenhui; Nakashima, Yuta; Qian, Yiming; Nagahara, Hajime

doi:https://doi.org/10.1007/s11042-025-20699-0

GNNBoost: boosting artwork classification with graph embeddings

El Vaigh, Cheikh Brahim; Garcia, Noa; Renoust, Benjamin et al.

Multimedia Tools and Applications, 2025

Number of Access:755（2025-08-15 01:09 Counts）

Identifier to cite or link to this item: https://hdl.handle.net/11094/101001

Link to primary information

File	Format	Terms of use	Size	Views	Date.Available	Description	information
MultimediaToolsAppl	pdf	None	1.62 MB	24	2025.04.17

Creative Commons : Attribution

Item Information

Output File Export EndNote Basic Export Mendeley

Title	GNNBoost: boosting artwork classification with graph embeddings
Creator	CreatorName El Vaigh, Cheikh Brahim
	NRID 1000080870005 1000080870005 ORCID 0000-0002-9200-6359 0000-0002-9200-6359 researchmap permalink noagarcia noagarcia Scopus Author ID 57201849958 57201849958 CreatorName Garcia, Noa
	CreatorName Renoust, Benjamin
	NRID 1000070784891 1000070784891 CreatorName Chu, Chenhui
	NRID 1000070633551 1000070633551 ORCID 0000-0001-8000-3567 0000-0001-8000-3567 researchmap permalink n-yuta n-yuta Scopus Author ID 56022946900 56022946900 CreatorName Nakashima, Yuta
	CreatorName Qian, Yiming
	NRID 1000080362648 1000080362648 ORCID 0000-0003-1579-8767 0000-0003-1579-8767 researchmap permalink read0054705 read0054705 Scopus Author ID 7006675539 7006675539 CreatorName Nagahara, Hajime
Subject	Artwork classification
	Focal Loss
	GNN
	Knowledge graph
	Label propagation
Description	The version of record of this article, first published in Multimedia Tools and Applications, is available online at Publisher’s website: https://doi.org/10.1007/s11042-025-20699-0
Abstract	The use of AI systems for managing large-scale cultural heritage artifacts has become possible due to the rise of digitization. To classify such content, machine learning is typically used, where contextual information is important to structure the data. One way to capture context is through a knowledge graph. In this study, we propose a newd graph neural networks, we can improve artwork classification by utilizing the relationships between entities of the knowledge graph. Our experiments demonstrate that this approach achieves state-of-the-art results on multiple classification tasks across three datasets (SemArt paintings, Buddha statues, and Ukiyo-e woodblock prints). Moreover, our approach is effective in dealing with unbalanced data and we explore the use of both graph attention mechanisms and focal loss functions.
Publisher	Springer
Source Title	Multimedia Tools and Applications
Date of Issued	2025-02-25
Language	English
Handle URL	https://hdl.handle.net/11094/101001
PISSN	13807501
eISSN	15737721
Relation.isIdenticalTo	DOI (Publisher Version) https://doi.org/10.1007/s11042-025-20699-0
Access Rights	open access
CopyRight	This article is licensed under a Creative Commons Attribution 4.0 International License.
oaire:version	Version of Record
Category	学術雑誌論文 Journal Article

Resource Type	journal article
Local Type	Journal Article
DCTERMS.bibliographicCitation	Multimedia Tools and Applications. 2025
DC.title	GNNBoost: boosting artwork classification with graph embeddings
DC.creator	El Vaigh, Cheikh Brahim
	Garcia, Noa
	Renoust, Benjamin
	Chu, Chenhui
	Nakashima, Yuta
	Qian, Yiming
	Nagahara, Hajime
DC.publisher	Springer
DC.language' scheme='DCTERMS.RFC1766	English
DCTERMS.issued' scheme='DCTERMS.W3CDTF	2025-02-25
DC.identifier	https://doi.org/10.1007/s11042-025-20699-0
DC.subject	Artwork classification
	Focal Loss
	GNN
	Knowledge graph
	Label propagation
DC.description	The version of record of this article, first published in Multimedia Tools and Applications, is available online at Publisher’s website: https://doi.org/10.1007/s11042-025-20699-0
DCTERMS.abstract	The use of AI systems for managing large-scale cultural heritage artifacts has become possible due to the rise of digitization. To classify such content, machine learning is typically used, where contextual information is important to structure the data. One way to capture context is through a knowledge graph. In this study, we propose a newd graph neural networks, we can improve artwork classification by utilizing the relationships between entities of the knowledge graph. Our experiments demonstrate that this approach achieves state-of-the-art results on multiple classification tasks across three datasets (SemArt paintings, Buddha statues, and Ukiyo-e woodblock prints). Moreover, our approach is effective in dealing with unbalanced data and we explore the use of both graph attention mechanisms and focal loss functions.
DC.rights	This article is licensed under a Creative Commons Attribution 4.0 International License.
DC.format	101001
citation_title	GNNBoost: boosting artwork classification with graph embeddings
citation_author	El Vaigh, Cheikh Brahim
	Garcia, Noa
	Renoust, Benjamin
	Chu, Chenhui
	Nakashima, Yuta
	Qian, Yiming
	Nagahara, Hajime
citation_publisher	Springer
citation_language	English
citation_date	2025-02-25
citation_journal_title	Multimedia Tools and Applications
citation_doi	https://doi.org/10.1007/s11042-025-20699-0
citation_public_url	https://hdl.handle.net/11094/101001

GNNBoost: boosting artwork classification with graph embeddings

Link to primary information

Item Information

Show details