用于神经符号知识图谱补全的逻辑规则简单增强方法
Simple Augmentations of Logical Rules for Neuro-Symbolic Knowledge Graph Completion
AI总结：
针对神经符号知识图谱补全中规则覆盖率不足的问题，本文提出溯因转换、逆关系等价规则和随机游走三种规则增强并剪枝低质规则，在多数据集上稳定提升MRR与Hits@1。
摘要：
高质量、高覆盖率的规则集对于神经符号知识图谱补全（NS-KGC）模型的成功至关重要，因为它们构成了所有符号推理的基础。近期文献构建了用于生成规则集的神经模型，然而初步实验表明，这些模型在保持高覆盖率方面存在困难。在本工作中，我们对现有规则集提出三种简单增强：（1）将规则转换为其溯因形式，（2）生成使用组成关系逆形式的等价规则，以及（3）通过随机游走提出新规则。最后，我们剪枝潜在低质量规则。在四个数据集和五种规则集基线设置上的实验表明，这些简单增强持续改善结果，并且相比使用未经增强的规则，最高获得7.1分MRR和8.5分Hits@1的提升。
英文摘要：
High-quality and high-coverage rule sets are imperative to the success of Neuro-Symbolic Knowledge Graph Completion (NS-KGC) models, because they form the basis of all symbolic inferences. Recent literature builds neural models for generating rule sets, however, preliminary experiments show that they struggle with maintaining high coverage. In this work, we suggest three simple augmentations to existing rule sets: (1) transforming rules to their abductive forms, (2) generating equivalent rules that use inverse forms of constituent relations and (3) random walks that propose new rules. Finally, we prune potentially low quality rules. Experiments over four datasets and five ruleset-baseline settings suggest that these simple augmentations consistently improve results, and obtain up to 7.1 pt MRR and 8.5 pt Hits@1 gains over using rules without augmentations.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
