Improved Knowledge Base Completion by Path-Augmented TransR Model

2016/10/06 by Wenhao Huang, Ge Li, Huang, Wenhao +3
Computer Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1610.04073

openalex publication_date 2016/10/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Knowledge base completion aims to infer new relations from existing information. In this paper, we propose path-augmented TransR (PTransR) model to improve the accuracy of link prediction. In our approach, we base PTransR model on TransR, which is the best one-hop model at present. Then we regularize TransR with information of relation paths. In our experiment, we evaluate PTransR on the task of entity prediction. Experimental results show that PTransR outperforms previous models.

Citations

• Traversing Knowledge Graphs in Vector Space
• Gene Ontology: tool for the unification of biology
• Classifying Relations by Ranking with Convolutional Neural Networks
• Modeling Relation Paths for Representation Learning of Knowledge Bases

Related

• Transductive Data Augmentation with Relational Path Rule Mining for Knowledge Graph Embedding
• KGRefiner: Knowledge Graph Refinement for Improving Accuracy of Translational Link Prediction Methods
• Combining Two And Three-Way Embeddings Models for Link Prediction in Knowledge Bases
• Representation Learning with Ordered Relation Paths for Knowledge Graph\n Completion
• Anchoring Path for Inductive Relation Prediction in Knowledge Graphs