Exploring Relational Semantics for Inductive Knowledge Graph Completion

Knowledge graph completion (KGC) aims to infer missing information in incomplete knowledge graphs (KGs). Most previous works only consider the transductive scenario where entities are existing in KGs, which cannot work effectively for the inductive scenario containing emerging entities. Recently some graph neural network-based methods have been proposed for inductive KGC by aggregating neighborhood information to capture some uncertainty semantics from the neighboring auxiliary triples. But these methods ignore the more general relational semantics underlying all the known triples that can provide richer information to represent emerging entities so as to satisfy the inductive scenario. In this paper, we propose a novel model called CFAG, which utilizes two granularity levels of relational semantics in a coarsegrained aggregator (CG-AGG) and a fine-grained generative adversarial net (FG-GAN), for inductive KGC. The CG-AGG firstly generates entity representations with multiple semantics through a hypergraph neural network-based global aggregator and a graph neural network-based local aggregator, and the FG-GAN further enhances entity representations with specific semantics through conditional generative adversarial nets. Experimental results on benchmark datasets show that our model outperforms state-of-the-art models for inductive KGC.

Authors

• Changjian Wang National University of Defense Technology
• Xiaofei Zhou Hangzhou Dianzi University
• Shirui Pan Griffith University, Queensland, Australia
• Linhua Dong
• Zeliang Song
• Ying Sha Key Laboratory of Smart Farming for Agricultural Animals, Wuhan, China Engineering Research Center of Intelligent Technology for Agriculture, Ministry of Education, Wuhan, China Hubei Engineering Technology Research Center of Agricultural Big Data, Wuhan, China College of Informatics, Huazhong Agricultural University, Wuhan, China

Keywords

No keywords are indexed for this paper.