Directed Knowledge Graph Embedding Using a Hybrid Architecture of Spatial and Spectral GNNs

Directed Knowledge Graph Embedding Using a Hybrid Architecture of Spatial and Spectral GNNs

Knowledge graph embedding has been identified as an effective method for node-level classification tasks in directed graphs, the objective of which is to ensure that nodes of different categories are embedded as far apart as possible in the feature space. The directed graph is a general representati...

Cijeli opis

Bibliografski detalji
Glavni autori: Guoqiang Hou, Qiwen Yu, Fan Chen, Guang Chen
Format: Članak
Jezik:English
Izdano: MDPI AG 2024-11-01
Serija:Mathematics
Teme:
knowledge graph embeddings
hybrid architecture
graph transformer
directed spectral graph convolution networks
node-level representation learning
Online pristup:https://www.mdpi.com/2227-7390/12/23/3689

Internet

https://www.mdpi.com/2227-7390/12/23/3689

Slični predmeti