Survey details GNN applications across knowledge graph technologies

This paper provides a comprehensive survey of how Graph Neural Networks (GNNs) are applied to knowledge graph technologies. It introduces a novel taxonomy that categorizes GNN-based KG methods across the entire KG pipeline, including construction, embedding, reasoning, and applications. The survey details various GNN models like GCN, GAT, and HGNN, analyzing their strengths and limitations in different KG lifecycle tasks. Finally, it discusses current challenges and future research directions in this interdisciplinary field. AI

IMPACT Provides a structured overview of GNN applications in knowledge graphs, aiding researchers and practitioners in understanding the landscape and identifying future research avenues.

RANK_REASON The item is an academic survey paper on arXiv. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• graph attention network
• graph convolutional network
• graph neural network
• graph neural networks
• hypergraph neural network
• knowledge graph

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →