Inductive Knowledge Graph Completion with GNNs and Rules: An Analysis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911811069018112 |
|---|---|
| author | Anil, Akash Gutiérrez-Basulto, Víctor Ibañéz-García, Yazmín Schockaert, Steven |
| author_facet | Anil, Akash Gutiérrez-Basulto, Víctor Ibañéz-García, Yazmín Schockaert, Steven |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_07942 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Inductive Knowledge Graph Completion with GNNs and Rules: An Analysis Anil, Akash Gutiérrez-Basulto, Víctor Ibañéz-García, Yazmín Schockaert, Steven Artificial Intelligence Machine Learning Social and Information Networks 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. |
| title | Inductive Knowledge Graph Completion with GNNs and Rules: An Analysis |
| topic | Artificial Intelligence Machine Learning Social and Information Networks |
| url | https://arxiv.org/abs/2308.07942 |