Path-based Link Prediction on Hyper-relational Knowledge Graph

Anonymous

Abstract: Recently, path-based Graph Neural Networks (GNNs) achieve promising performance of the link prediction task on benchmark Knowledge Graphs (KGs). However, there is no research on leveraging path-based GNNs to promote the more general case of KGs, namely hyper-relational KGs (HKGs). To bridge this research gap, we study the path-based GNNs and discover that existing path-based GNNs fail to handle HKGs because they cannot well explore the external information (i.e., qualifiers) stored in HKGs. In this paper, we propose a novel framework, Hyper Path-based Graph Neural Network (HyperPGNN) for HKGs. Specifically, we propose a novel Hyper2Tri conversion and hyper query learner to better enable the path-based GNNs to understand qualifiers in HKG, then capture them into the graph learning. Results show our method outperforms SOTA performance in both transductive and inductive settings.

Paper Type: short

Research Area: Machine Learning for NLP

Contribution Types: NLP engineering experiment, Publicly available software and/or pre-trained models

Languages Studied: English;

Consent To Share Submission Details: On behalf of all authors, we agree to the terms above to share our submission details.