Inductive Knowledge Graph Completion with GNNs and Rules: An Analysis

Akash Anil, Victor Gutierrez-Basulto, Yazmin Ibanez-Garcia, Steven Schockaert


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.
Anthology ID:
2024.lrec-main.792
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
9036–9049
Language:
URL:
https://aclanthology.org/2024.lrec-main.792
DOI:
Bibkey:
Cite (ACL):
Akash Anil, Victor Gutierrez-Basulto, Yazmin Ibanez-Garcia, and Steven Schockaert. 2024. Inductive Knowledge Graph Completion with GNNs and Rules: An Analysis. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 9036–9049, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Inductive Knowledge Graph Completion with GNNs and Rules: An Analysis (Anil et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.792.pdf