Crossref
Enhancing information flow in graph neural networks through geometry-preserving hierarchical connectivity
Computers & Structures · 2026-12 · 333 · 108498
DOI: 10.1016/j.compstruc.2026.108498 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computers & Structures, 2026-12. Verfasst von Marien Chenaud und 2 weiteren Autor:innen. Die Arbeit nennt 76 Literaturangaben.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Zitieren
APA
Chenaud, M., Alves, J., & Magoulès, F. (2026). Enhancing information flow in graph neural networks through geometry-preserving hierarchical connectivity. Computers & Structures, 333, 108498. https://doi.org/10.1016/j.compstruc.2026.108498
Vancouver
Chenaud M, Alves J, Magoulès F. Enhancing information flow in graph neural networks through geometry-preserving hierarchical connectivity. Computers & Structures. 2026;333:108498. doi:10.1016/j.compstruc.2026.108498
BibTeX
@article{Chenaud2026,
author = {Chenaud, Marien and Alves, José and Magoulès, Frédéric},
title = {Enhancing information flow in graph neural networks through geometry-preserving hierarchical connectivity},
journal = {Computers & Structures},
year = {2026},
volume = {333},
pages = {108498},
doi = {10.1016/j.compstruc.2026.108498}
}
EUVIMED