Towards Enhancing Relational Rules for Knowledge Graph Link Prediction

Shuhan Wu, Huaiyu Wan, Wei Chen, Yuting Wu, Junfeng Shen, Youfang Lin

Abstract
Graph neural networks (GNNs) have shown promising performance for knowledge graph reasoning. A recent variant of GNN called progressive relational graph neural network (PRGNN), utilizes relational rules to infer missing knowledge in relational digraphs and achieves notable results. However, during reasoning with PRGNN, two important properties are often overlooked: (1) the sequentiality of relation composition, where the order of combining different relations affects the semantics of the relational rules, and (2) the lagged entity information propagation, where the transmission speed of required information lags behind the appearance speed of new entities. Ignoring these properties leads to incorrect relational rule learning and decreased reasoning accuracy. To address these issues, we propose a novel knowledge graph reasoning approach, the Relational rUle eNhanced Graph Neural Network (RUN-GNN). Specifically, RUN-GNN employs a query related fusion gate unit to model the sequentiality of relation composition and utilizes a buffering update mechanism to alleviate the negative effect of lagged entity information propagation, resulting in higher-quality relational rule learning. Experimental results on multiple datasets demonstrate the superiority of RUN-GNN is superior on both transductive and inductive link prediction tasks.
Anthology ID:
2023.findings-emnlp.676
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10082–10097
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.676
DOI:
10.18653/v1/2023.findings-emnlp.676
Bibkey:
Cite (ACL):
Shuhan Wu, Huaiyu Wan, Wei Chen, Yuting Wu, Junfeng Shen, and Youfang Lin. 2023. Towards Enhancing Relational Rules for Knowledge Graph Link Prediction. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 10082–10097, Singapore. Association for Computational Linguistics.
Cite (Informal):
Towards Enhancing Relational Rules for Knowledge Graph Link Prediction (Wu et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2023.findings-emnlp.676.pdf
PDF Search