Exploring Relational Semantics for Inductive Knowledge Graph Completion

Authors

  • Changjian Wang Institute of Information Engineering, Chinese Academy of Sciences School of Cyber Security, University of Chinese Academy of Sciences
  • Xiaofei Zhou Institute of Information Engineering, Chinese Academy of Sciences School of Cyber Security, University of Chinese Academy of Sciences
  • Shirui Pan Faculty of Information Technology, Monash University
  • Linhua Dong Institute of Information Engineering, Chinese Academy of Sciences School of Cyber Security, University of Chinese Academy of Sciences
  • Zeliang Song Institute of Information Engineering, Chinese Academy of Sciences School of Cyber Security, University of Chinese Academy of Sciences
  • Ying Sha College of Informatics, Huazhong Agricultural University

DOI:

https://doi.org/10.1609/aaai.v36i4.20337

Keywords:

Data Mining & Knowledge Management (DMKM), Machine Learning (ML)

Abstract

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 coarse-grained 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.

Downloads

Published

2022-06-28

How to Cite

Wang, C., Zhou, X., Pan, S., Dong, L., Song, Z., & Sha, Y. (2022). Exploring Relational Semantics for Inductive Knowledge Graph Completion. Proceedings of the AAAI Conference on Artificial Intelligence, 36(4), 4184-4192. https://doi.org/10.1609/aaai.v36i4.20337

Issue

Section

AAAI Technical Track on Data Mining and Knowledge Management