Inductive Knowledge Graph Completion with GNNs and Rules: An Analysis

TL;DR

This paper analyzes the limitations of rule-based methods for inductive knowledge graph completion and proposes variants that improve performance while maintaining interpretability, with one variant outperforming state-of-the-art GNN-based models.

Contribution

It identifies key factors limiting rule-based methods and introduces variants that enhance their effectiveness, bridging the gap with GNN-based models.

Findings

Variants achieve performance close to NBFNet

Full KG analysis further improves results

Rule-based methods retain interpretability

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.