Type-augmented Relation Prediction in Knowledge Graphs

Abstract

Knowledge graphs (KGs) are of great importance to many real world applications, but they generally suffer from incomplete information in the form of missing relations between entities. Knowledge graph completion (also known as relation prediction) is the task of inferring missing facts given existing ones. Most of the existing work is proposed by maximizing the likelihood of observed instance-level triples. Not much attention, however, is paid to the ontological information, such as type information of entities and relations. In this work, we propose a type-augmented relation prediction (TaRP) method, where we apply both the type information and instance-level information for relation prediction. In particular, type information and instance-level information are encoded as prior probabilities and likelihoods of relations respectively, and are combined by following Bayes' rule. Our proposed TaRP method achieves significantly better performance than state-of-the-art methods on four benchmark datasets: FB15K, FB15K-237, YAGO26K-906, and DB111K-174. In addition, we show that TaRP achieves significantly improved data efficiency. More importantly, the type information extracted from a specific dataset can generalize well to other datasets through the proposed TaRP model.

References in corpus (7)

• KGAT: Knowledge Graph Attention Network for Recommendation
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• Quaternion Knowledge Graph Embeddings
• Hypernetwork Knowledge Graph Embeddings
• SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions
• Variational Knowledge Graph Reasoning
• Bridging Knowledge Graphs to Generate Scene Graphs