AILGSIAug 14, 2023

Inductive Knowledge Graph Completion with GNNs and Rules: An Analysis

arXiv:2308.07942v282 citationsh-index: 31
Originality Incremental advance
AI Analysis

This work addresses the problem of improving interpretability and efficiency in knowledge graph completion for AI researchers, though it is incremental as it builds on existing rule-based and GNN methods.

The paper tackled the underperformance of rule-based methods in inductive knowledge graph completion compared to GNN-based methods like NBFNet, finding that addressing issues such as implausible entity ranking and limited path consideration allowed rule-based variants to achieve close or superior performance while maintaining interpretability.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes