Inductive knowledge graph completion with GNNs and rules: An analysis

Akash Anil, Akash, Gutierrez Basulto, Victor ORCID: https://orcid.org/0000-0002-6117-5459, Ibanez Garcia, Yazmin ORCID: https://orcid.org/0000-0002-1276-904X and Schockaert, Steven ORCID: https://orcid.org/0000-0002-9256-2881 2024. Inductive knowledge graph completion with GNNs and rules: An analysis. Presented at: 2024 Joint International Conference On Computational Linguistics, Language Resources And Evaluation (LREC-COLING 2024), Turin, Italy, 20-25 May 2024. Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation. ELRA and ICCL, pp. 9036-9049.

Preview

PDF - Published Version Available under License Creative Commons Attribution Non-commercial. Download (1MB) | Preview

Abstract

The task of inductive knowledge graph completion requires models to learn inference patterns from a training graph, which can then be used to make predictions on a disjoint test graph. Rule-based methods seem like a natural fit for this task, but in practice they significantly underperform state-of-the-art methods based on Graph Neural Networks (GNNs), such as NBFNet. We hypothesise that the underperformance of rule-based methods is due to two factors: (i) implausible entities are not ranked at all and (ii) only the most informative path is taken into account when determining the confidence in a given link prediction answer. To analyse the impact of these factors, we study a number of variants of a rule-based approach, which are specifically aimed at addressing the aforementioned issues. We find that the resulting models can achieve a performance which is close to that of NBFNet. Crucially, the considered variants only use a small fraction of the evidence that NBFNet relies on, which means that they largely keep the interpretability advantage of rule-based methods. Moreover, we show that a further variant, which does look at the full KG, consistently outperforms NBFNet.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Publication
Status:	Published
Schools:	Professional Services > Advanced Research Computing @ Cardiff (ARCCA) Schools > Computer Science & Informatics
Publisher:	ELRA and ICCL
ISBN:	978-249381410-4
Funders:	Leverhulme Trust
Date of First Compliant Deposit:	3 April 2024
Date of Acceptance:	19 February 2024
Last Modified:	18 Feb 2025 16:10
URI:	https://orca.cardiff.ac.uk/id/eprint/167693

Actions (repository staff only)

Edit Item