In this technical report, we investigate the predictive performance differences of a rule-based approach and the GNN architectures NBFNet and A*Net with respect to knowledge graph completion. For the two most common benchmarks, we find that a substantial fraction of the performance difference can be explained by one unique negative pattern on each dataset that is hidden from the rule-based approach. Our findings add a unique perspective on the performance difference of different model classes for knowledge graph completion: Models can achieve a predictive performance advantage by penalizing scores of incorrect facts opposed to providing high scores for correct facts.

翻译：在本技术报告中，我们研究了基于规则的方法与图神经网络架构NBFNet和A*Net在知识图谱补全任务中的预测性能差异。针对两个最常用的基准数据集，我们发现性能差异的相当大部分可通过每个数据集中隐藏于规则方法之外的一种独特负向模式来解释。我们的研究结果为知识图谱补全中不同模型类别的性能差异提供了独特视角：模型可以通过抑制错误事实的评分而非仅提升正确事实的评分来获得预测性能优势。