KGRefiner: Knowledge Graph Refinement for Improving Accuracy of Translational Link Prediction Methods

27 Jun 2021  ·  Mohammad Javad Saeedizade, Najmeh Torabian, Behrouz Minaei-Bidgoli ·

The Link Prediction is the task of predicting missing relations between entities of the knowledge graph. Recent work in link prediction has attempted to provide a model for increasing link prediction accuracy by using more layers in neural network architecture. In this paper, we propose a novel method of refining the knowledge graph so that link prediction operation can be performed more accurately using relatively fast translational models. Translational link prediction models, such as TransE, TransH, TransD, have less complexity than deep learning approaches. Our method uses the hierarchy of relationships and entities in the knowledge graph to add the entity information as auxiliary nodes to the graph and connect them to the nodes which contain this information in their hierarchy. Our experiments show that our method can significantly increase the performance of translational link prediction methods in H@10, MR, MRR.

PDF Abstract

Results from the Paper

Ranked #2 on Link Prediction on FB15k-237 (training time (s) metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Link Prediction FB15k-237 KGRefiner MRR 0.302 # 53
Hits@10 0.489 # 50
MR 203 # 18
training time (s) 1100 # 2
Link Prediction WN18RR KGRefiner MRR 0.448 # 47
Hits@10 0.57 # 26
MR 683 # 4