Back to feed
arXiv cs.LG
arXiv cs.LG
7/14/2026
Knowledge Graphs Meet Graph Neural Networks: A Comprehensive Survey

Knowledge Graphs Meet Graph Neural Networks: A Comprehensive Survey

Short summary

This comprehensive survey proposes a two-level taxonomy for GNN-based knowledge graph technologies, covering the KG pipeline (construction, embedding, reasoning, applications) and GNN model perspectives (GCN, GAT, HGNN). The authors review GNN-based models across the KG lifecycle, analyzing strengths and limitations for each task type. They conclude with unresolved challenges and future research directions at the intersection of GNNs and knowledge graphs.

  • •Two-level taxonomy: KG pipeline stages × GNN model types
  • •Reviews GNN-based models for KG construction, embedding, reasoning, and applications
  • •Identifies open challenges and future research directions

Generated with AI, which can make mistakes.

#research-breakthrough
Read full article at arXiv cs.LG

Is this a good recommendation for you?

Comments

Failed to load comments. Please try again.

Explore more

The user wants me to rewrite a news headline for a mobile feed based on the original title and summary.
arXiv CS.AI
The original title is: "Graph Neural Networks: Theoretical Foundations and Core Mechanisms Explained"
Dev.to
Enhancing Small Language Models Reasoning through Knowledge Graph Grounding
arXiv CS.AI
HG-RAG: Hierarchy-Guided Retrieval-Augmented Generation for Structured Knowledge Graphs
arXiv CS.AI