.png){kind=icon}
.png){kind=icon}
Return
An explainable path reasoning framework for knowledge graph completion
.png){kind=icon}
OA
AI
DOI：10.1016/j.aej.2025.12.024.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Propose an Explainable Path Reasoning (EPR) framework for knowledge graph completion. • Synergize statistical path mining with a unified BERT-based semantic reasoner. • A single architecture jointly generates predictions and faithful multi-hop explanations. • Achieve competitive results among explainable models, narrowing the performance gap. • Demonstrate that concise paths (2-3 hops) are sufficient for robust reasoning.
Keywords:
Deep learning
Knowledge graph completion
Representation learning
Explainable AI
Semantic communication
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.8
Papers:
6.3K
Citations:
2.6W
Organization
View more organizations