[论文解读] Knowledge Graph Embedding for Link Prediction: A Comparative Analysis

Andrea Rossi, Donatella Firmani+3 more|arXiv (Cornell University)|Feb 3, 2020

Advanced Graph Neural Networks参考文献 70被引用 141

一句话总结

该论文对16个基于KG嵌入的链接预测模型在流行基准数据集上进行了从头开始的全面比较，强调方法差异和评估实践。

ABSTRACT

Knowledge Graphs (KGs) have found many applications in industry and academic settings, which in turn, have motivated considerable research efforts towards large-scale information extraction from a variety of sources. Despite such efforts, it is well known that even state-of-the-art KGs suffer from incompleteness. Link Prediction (LP), the task of predicting missing facts among entities already a KG, is a promising and widely studied task aimed at addressing KG incompleteness. Among the recent LP techniques, those based on KG embeddings have achieved very promising performances in some benchmarks. Despite the fast growing literature in the subject, insufficient attention has been paid to the effect of the various design choices in those methods. Moreover, the standard practice in this area is to report accuracy by aggregating over a large number of test facts in which some entities are over-represented; this allows LP methods to exhibit good performance by just attending to structural properties that include such entities, while ignoring the remaining majority of the KG. This analysis provides a comprehensive comparison of embedding-based LP methods, extending the dimensions of analysis beyond what is commonly available in the literature. We experimentally compare effectiveness and efficiency of 16 state-of-the-art methods, consider a rule-based baseline, and report detailed analysis over the most popular benchmarks in the literature.

研究动机与目标

• 通过嵌入来评估链接预测，以解决知识图谱中的不完整性。
• 提供一个大规模、公平的比较分析，超越聚合测试准确率。
• 详述跨体系结构的设计选择如何影响链接预测（LP）在常见基准上的性能。
• 提出有启发性的评估实践，并公开可用的数据集、代码和结果。

提出的方法

• 从头开始训练和调优16个嵌入式LP模型，以及一个基于规则的基线。
• 比较多样化的架构：张量分解、几何模型与深度学习模型。
• 在最常用的5个LP数据集上使用标准指标进行评估。
• 定义训练数据的结构特征并衡量它们对预测性能的影响。
• 提供每个预测的排序和CSV输出以便进行更深层次的分析。
• 通过公开的GitHub仓库分享代码和资源。

实验结果

研究问题

• RQ1 在标准LP基准上，哪些知识图嵌入模型在有效性与效率之间提供最佳折衷？
• RQ2 设计选择（张量式与几何式、深度学习之间的设计、双线性 vs 非双线性、平移型 vs 旋转型）如何影响链接预测性能？
• RQ3 数据集特征如何影响模型性能，以及哪些因素能预测易预测和难预测？
• RQ4 当前的评估实践是否能准确反映跨知识图的模型能力？

主要发现

• 对16个最先进的模型在5个数据集上进行了实验证比较。
• 该研究提供了超越原始论文的详细结果，包括每个模型和数据集的效率与效能。
• 定义了一组训练数据的结构特征，以评估它们对模型性能的影响。
• 结果包括每个预测的排名和完整的预测列表，以实现透明性。
• 数据集、代码和资源在GitHub上公开可用。