Por favor, use este identificador para citar o enlazar este ítem:
http://hdl.handle.net/10609/150374
Registro completo de metadatos
Campo DC | Valor | Lengua/Idioma |
---|---|---|
dc.contributor.author | Alvarez-Gonzalez, Nurudin | - |
dc.contributor.author | Kaltenbrunner, Andreas | - |
dc.contributor.author | Gómez, Vicenç | - |
dc.date.accessioned | 2024-05-30T09:58:54Z | - |
dc.date.available | 2024-05-30T09:58:54Z | - |
dc.date.issued | 2023-09-22 | - |
dc.identifier.citation | Alvarez-Gonzalez, N, [Nurudin], Kaltenbrunner, A. [Andreas], Gómez, V. [Vicenç]. (2023). Beyond Weisfeiler–Lehman with Local Ego-Network Encodings. Machine Learning and Knowledge Extraction, 5(4). doi: 10.3390/make5040063 | - |
dc.identifier.issn | 2504-4990MIAR | - |
dc.identifier.uri | http://hdl.handle.net/10609/150374 | - |
dc.description.abstract | Identifying similar network structures is key to capturing graph isomorphisms and learning representations that exploit structural information encoded in graph data. This work shows that ego networks can produce a structural encoding scheme for arbitrary graphs with greater expressivity than the Weisfeiler–Lehman (1-WL) test. We introduce IGEL, a preprocessing step to produce features that augment node representations by encoding ego networks into sparse vectors that enrich message passing (MP) graph neural networks (GNNs) beyond 1-WL expressivity. We formally describe the relation between IGEL and 1-WL, and characterize its expressive power and limitations. Experiments show that IGEL matches the empirical expressivity of state-of-the-art methods on isomorphism detection while improving performance on nine GNN architectures and six graph machine learning tasks. | en |
dc.format.mimetype | application/pdf | - |
dc.language.iso | eng | ca |
dc.publisher | MDPI AG | - |
dc.relation.ispartof | Machine Learning and Knowledge Extraction (MAKE), 2023, 5(4) | - |
dc.relation.uri | https://doi.org/10.3390/make5040063 | - |
dc.rights | CC BY | - |
dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | - |
dc.subject | graph neural networks | en |
dc.subject | graph representation learning | en |
dc.subject | weisfeiler–lehman | en |
dc.subject | graph isomorphism | en |
dc.subject | GNN expressivity | en |
dc.subject | ego networks | en |
dc.title | Beyond Weisfeiler–Lehman with Local Ego-Network Encodings | en |
dc.type | info:eu-repo/semantics/article | - |
dc.rights.accessRights | info:eu-repo/semantics/openAccess | - |
dc.identifier.doi | https://doi.org/10.3390/make5040063 | - |
dc.gir.id | AR/0000011187 | - |
dc.relation.projectID | info:eu-repo/grantAgreement/MCIN/AEI/CEX2021-001195-M ; info:eu-repo/grantAgreement/MCIN/AEI/CNS2022-136178 | - |
dc.type.version | info:eu-repo/semantics/publishedVersion | - |
Aparece en las colecciones: | Articles cientÍfics Articles |
Ficheros en este ítem:
Fichero | Descripción | Tamaño | Formato | |
---|---|---|---|---|
Beyond_Weisfeiler_Lehman_with_Local_Ego_Network_Encodings.pdf | 1,2 MB | Adobe PDF | ![]() Visualizar/Abrir |
Comparte:
![]( /image/googleScholar.png)
![](/image/microsoftAcademic.png)
Los ítems del Repositorio están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.