WeExt: A Framework of Extending Deterministic Knowledge Graph Embedding Models for Embedding Weighted Knowledge Graphs

Abstract

With the further development of knowledge graphs, many weighted knowledge graphs (WKGs) have been published and greatly promote various applications. However, current deterministic knowledge graph embedding algorithms cannot encode weighted knowledge graphs well. This paper gives a promising framework WeExt that can extend deterministic knowledge graph embedding models to enable them to learn weighted knowledge graph embeddings. In addtion, we introduce weighted link prediction to evaluate the weighted knowledge graph embedding models' performance on completing WKGs. Finally, we give concrete implementation of WeExt based on two translational distance models and two semantic matching models. Our experimental results show the proposed framework achieves promising performance in link prediction, weight prediction, and weighted link prediction.