Comprehensive Survey Maps GNNs Across Knowledge Graph Lifecycle

Chengcheng Sun, Jiayun Tian, Cheng Zhai, Zhixiao Wang, Yajie Song, Xiaobin Rui, Jian Zhang, Philip S. Yu· July 14, 2026 View original

▶ The 2-minute explainer

Summary

This survey provides a two-level taxonomy for understanding how Graph Neural Networks (GNNs) are applied across the entire knowledge graph technology pipeline, from construction and embedding to reasoning and applications. It details various GNN models, their strengths, limitations, and future research directions in KGs.

Graph Neural Networks (GNNs) have become a powerful method for working with Knowledge Graphs (KGs) due to their inherent ability to process graph-structured data. Despite their growing use, a comprehensive review systematically mapping GNN-based methodologies across the full KG technology pipeline has been lacking. This survey aims to fill that gap by proposing a novel two-level taxonomy. The taxonomy organizes GNN applications first by the KG technology pipeline, covering stages like KG construction, embedding, reasoning, and various applications. Second, it categorizes these technologies from a GNN-based perspective, detailing how specific GNN models such as GCN, GAT, and HGNN are utilized. The survey analyzes the advantages of GNNs for different tasks within the KG lifecycle, reviews various GNN-based models according to this taxonomy, and summarizes their respective strengths and limitations. Finally, it discusses unresolved challenges and outlines promising future research directions in the intersection of KGs and GNNs.

Why it matters

For professionals working with complex data relationships, this survey offers a structured overview of how GNNs can enhance knowledge graph capabilities, from building better KGs to extracting more intelligent insights. It's a valuable resource for adopting advanced AI techniques in data management.

How to implement this in your domain

  1. 1Consult the survey to identify suitable GNN models for specific knowledge graph tasks (e.g., entity linking, relation extraction, reasoning).
  2. 2Evaluate existing GNN-based tools and libraries for knowledge graph construction and embedding.
  3. 3Explore how GNNs can improve knowledge reasoning capabilities in your applications.
  4. 4Stay updated on the discussed challenges and future directions to inform your R&D strategy in KG and GNN integration.

Who benefits

Data ScienceAI/ML DevelopmentSemantic WebEnterprise SearchHealthcare

Key takeaways

  • GNNs are increasingly vital for various stages of the knowledge graph lifecycle.
  • A new taxonomy categorizes GNN applications in KGs by pipeline stage and GNN model type.
  • The survey details strengths, limitations, and future directions for GNNs in KGs.
  • It serves as a comprehensive guide for integrating GNNs into knowledge graph technologies.

Original post by Chengcheng Sun, Jiayun Tian, Cheng Zhai, Zhixiao Wang, Yajie Song, Xiaobin Rui, Jian Zhang, Philip S. Yu

"arXiv:2607.09666v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have emerged as a powerful paradigm in Knowledge Graphs (KGs) due to their intrinsic ability to model graph-structured data. However, there remains a lack of a systematic review about GNN-based methodolo…"

View on X

Originally posted by Chengcheng Sun, Jiayun Tian, Cheng Zhai, Zhixiao Wang, Yajie Song, Xiaobin Rui, Jian Zhang, Philip S. Yu on X · view source

Want to go deeper?

Turn these trends into skills with Learnijoy's hands-on AI & tech courses.

Explore courses