Concept information
Terme préférentiel
graph attention network
Définition
- A neural network architecture for graph-structured data that uses masked self-attentional layers to overcome the limitations of prior approaches based on graph convolutions and their approximations. (Based on Waikhom and Patgiri, Principles of Big Graph: In-depth Insight, in Advances in Computers, 2023)
Concept générique
Synonyme(s)
- GAT
Traductions
-
français
URI
http://data.loterre.fr/ark:/67375/8LP-ZGV1ZTXP-L
{{label}}
{{#each values }} {{! loop through ConceptPropertyValue objects }}
{{#if prefLabel }}
{{/if}}
{{/each}}
{{#if notation }}{{ notation }} {{/if}}{{ prefLabel }}
{{#ifDifferentLabelLang lang }} ({{ lang }}){{/ifDifferentLabelLang}}
{{#if vocabName }}
{{ vocabName }}
{{/if}}