QR kód

JGURD: joint gradient update relational direction-enhanced method for knowledge graph completion

Relational direction plays an important role in multi-relational knowledge graphs (KGs). Current knowledge graph completion (KGC) methods suffer from insufficient utilization of relation correlation information. To address this issue, this article proposes a novel KGC framework, namely JGURD, which...

Celý popis

Uloženo v:
Hlavní autoři: Lianhong Ding, Mengxiao Li, Shengchang Gao, Juntao Li, Ruiping Yuan, Jianye Yu
Médium: Artigo
Jazyk:Inglês
Vydáno: PeerJ Inc. 2025-04-01
Edice:PeerJ Computer Science
Témata:
Knowledge graph completion
Graph neural networks
Joint gradient update
Link prediction
Relational direction
Encoder-decoder
On-line přístup:https://peerj.com/articles/cs-2808.pdf
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Podobné jednotky