A*Net与NBFNet通过学习负样本模式提升知识图谱补全性能。
A*Net and NBFNet Learn Negative Patterns on Knowledge Graphs
- 通过识别并惩罚错误事实得分，提升预测准确性
- 在两个主流数据集上，负模式解释了大部分性能差异
- 适合关注知识图谱推理机制的研究者
本技术报告研究了基于规则的方法与GNN架构NBFNet和A*Net在知识图谱补全任务中的预测性能差异。在两个最常用的基准数据集上，我们发现大量性能差异可由每项数据集中一个独特的隐藏负模式解释，该模式被基于规则的方法忽略。研究揭示了不同模型类在知识图谱补全中的性能差异新视角：模型可通过惩罚错误事实得分，而非仅提高正确事实得分，获得预测优势。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。