期刊论文

Jin Liu

英文

Information Processing & Management

0306-4573

2022

59

6

103076

10.1016/j.ipm.2022.103076

This work was supported by the National Natural Science Foundation of China under Grants 61972290 and 61972173 , the National Key R&D Program of China under Grant 2018YFC1604000 , the Fundamental Research Funds for the Central Universities (No. CCNU22QN015 ), and Wuhan knowledge innovation project (No. 2022010801010278 ). This work was also supported by the Natural Sciences and Engineering Research Council (NSERC) of Canada , an NSERC CREATE award in ADERSIM, 4 4 the York Research Chairs (YRC) program and an ORF-RE (Ontario Research Fund-Research Excellence) award in BRAIN Alliance. 5 5 The Authors thank the anonymous reviewers and the associate editor for their insightful comments.

本校为其他机构

Knowledge graph representation learning (KGRL) aims to infer the missing links between target entities based on existing triples. Graph neural networks (GNNs) have been introduced recently as one of the latest trendy architectures serves KGRL task using aggregations of neighborhood information. However, current GNN-based methods have fundamental limitations in both modelling the multi-hop distant neighbors and selecting relation-specific neighborhood information from vast neighbors. In this study, we propose a new relation-specific graph transformation network (RGTN) for the KGRL task. Specifi...