Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Pina, Oscar"'
Autor:
Pina, Oscar, Vilaplana, Verónica
End-to-end training of graph neural networks (GNN) on large graphs presents several memory and computational challenges, and limits the application to shallow architectures as depth exponentially increases the memory and space complexities. In this m
Externí odkaz:
http://arxiv.org/abs/2309.01503
Autor:
Pina, Oscar, Vilaplana, Verónica
Self-supervised learning is gaining considerable attention as a solution to avoid the requirement of extensive annotations in representation learning on graphs. Current algorithms are based on contrastive learning, which is computation an memory expe
Externí odkaz:
http://arxiv.org/abs/2303.08644
Autor:
Pérez-Cano, Jose, Sansano Valero, Irene, Anglada-Rotger, David, Pina, Oscar, Salembier, Philippe, Marques, Ferran
Publikováno v:
In Heliyon 15 April 2024 10(7)
Autor:
Cuenca-Pardo, Jesús, Ramos-Gallardo, Guillermo, Morales-Olivera, Martín, Contreras-Bulnes, Livia, Bucio-Duarte, Javier, Iribarren-Moreno, Rufino, Vélez-Benítez, Estela, Domínguez-Millán, Rodrigo, Salmean-Piña, Oscar
Publikováno v:
In Journal of Plastic, Reconstructive & Aesthetic Surgery August 2023 83:361-372
Autor:
Pina, Oscar, Vilaplana, Verónica
Self-supervised learning is gaining considerable attention as a solution to avoid the requirement of extensive annotations in representation learning on graphs. We introduce \textit{Regularized Graph Infomax (RGI)}, a simple yet effective framework f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9ca38c5cb026127fa58b54c98977a311
Autor:
Ceballos Pina, Oscar
Publikováno v:
idUS. Depósito de Investigación de la Universidad de Sevilla
instname
instname
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::7953380a52c500007678b02fc85a5190
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.