dc.creator | Sola Espinosa, Fernando Luis | es |
dc.creator | Ayala Hernández, Daniel | es |
dc.creator | Hernández Salmerón, Inmaculada Concepción | es |
dc.creator | Ruiz Cortés, David | es |
dc.date.accessioned | 2023-06-28T11:30:21Z | |
dc.date.available | 2023-06-28T11:30:21Z | |
dc.date.issued | 2023-06-28 | |
dc.identifier.citation | Sola, F.d., Ayala Hernández, D., Hernández Salmerón, I.C. y Ruiz Cortés, D. (2023). Deep embeddings and Graph Neural Networks: using context to improve domain-independent predictions. Applied Intelligence. https://doi.org/10.1007/s10489-023-04685-3. | |
dc.identifier.issn | 0924-669X (impreso) | es |
dc.identifier.issn | 1573-7497 (online) | es |
dc.identifier.uri | https://hdl.handle.net/11441/147545 | |
dc.description.abstract | Graph neural networks (GNNs) are deep learning architectures that apply graph convolutions through message-passing processes between nodes, represented as embeddings. GNNs have recently become popular because of their ability to obtain a contextual representation of each node taking into account information from its surroundings. However, existing work has focused on the development of GNN architectures, using basic domain-specific information about the nodes to compute embeddings. Meanwhile, in the closely-related area of knowledge graphs, much effort has been put towards developing deep learning techniques to obtain node embeddings that preserve information about relationships and structure without relying on domain-specific data. The potential application of deep embeddings of knowledge graphs in GNNs remains largely unexplored. In this paper, we carry out a number of experiments to answer open research questions about the impact on GNNs performance when combined with deep embeddings. We test 7 different deep embeddings across several attribute prediction tasks in two state-of-art attribute-rich datasets. We conclude that, while there is a significant performance improvement, its magnitude varies heavily depending on the specific task and deep embedding technique considered. | es |
dc.description.sponsorship | Ministerio de Ciencia, Innovación y Universidades PID2019- 105471RB-I00 | es |
dc.description.sponsorship | Junta de Andalucía P18-RT-1060 | es |
dc.description.sponsorship | Junta de Andalucía US-1380565 | es |
dc.format | application/pdf | es |
dc.format.extent | 14 | es |
dc.language.iso | eng | es |
dc.publisher | SprigerLink | es |
dc.relation.ispartof | Applied Intelligence. | |
dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 Internacional | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | * |
dc.subject | Knowledge graphs | es |
dc.subject | Graph neural networks | es |
dc.subject | Attributive embeddings | es |
dc.subject | Deep graph embeddings | es |
dc.subject | Machine learning | es |
dc.title | Deep embeddings and Graph Neural Networks: using context to improve domain-independent predictions | es |
dc.type | info:eu-repo/semantics/article | es |
dcterms.identifier | https://ror.org/03yxnpp24 | |
dc.type.version | info:eu-repo/semantics/publishedVersion | es |
dc.rights.accessRights | info:eu-repo/semantics/openAccess | es |
dc.contributor.affiliation | Universidad de Sevilla. Departamento de Lenguajes y Sistemas Informáticos | es |
dc.relation.projectID | PID2019- 105471RB-I00 | es |
dc.relation.projectID | P18-RT-1060 | es |
dc.relation.projectID | US-1380565 | es |
dc.relation.publisherversion | https://link.springer.com/article/10.1007/s10489-023-04685-3 | es |
dc.identifier.doi | 10.1007/s10489-023-04685-3 | es |
dc.journaltitle | Applied Intelligence | es |
dc.contributor.funder | Ministerio de Ciencia, Innovación y Universidades (MICINN). España | es |
dc.contributor.funder | Junta de Andalucía | es |