Knowledge Graph Embedding for Link Prediction: A Comparative Analysis
Knowledge Graph Embedding for Link Prediction: A Comparative Analysis
复制标题
DOI：
10.1145/3424672
复制
发表时间：
2021-04-01
影响因子：
3.6
通讯作者：
Merialdo, Paolo
中科院分区：
文献类型：
--
作者：
Rossi, Andrea;Barbosa, Denilson;Merialdo, Paolo
知识图（KGS）在工业和学术环境中发现了许多应用，而这些应用程序又激发了大量研究工作，以从各种来源中提取大规模的信息。尽管做出了这样的努力，但众所周知，即使是最大的公斤也遭受了不完整的困扰。链接预测（LP）技术通过确定KG中已经存在的实体之间的丢失事实来解决此问题。在最近的LP技术中，基于KG嵌入的技术在某些基准测试中取得了非常有希望的性能。尽管对该主题有快速增长的文献，但在这些方法中设计选择的影响不足。此外，该领域的标准做法是通过汇总大量的测试事实来报告准确性，其中某些实体比其他实体更有代表性。这允许LP方法仅仅参与包括此类实体的结构特性，同时忽略其余大部分KG，从而表现出良好的结果。该分析提供了基于嵌入的LP方法的全面比较，从而将分析的维度扩展到了文献中常见的范围之外。我们在实验上比较了18种最先进方法的有效性和效率，请考虑基于规则的基线，并报告对文献中最流行的基准测试的详细分析。
Knowledge Graphs (KGs) have found many applications in industrial and in 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 the largest KGs suffer from incompleteness; Link Prediction (LP) techniques address this issue by identifying missing facts among entities already in the KG. Among the recent LP techniques, those based on KG embeddings have achieved very promising performance in some benchmarks. Despite the fast-growing literature on the subject, insufficient attention has been paid to the effect of the 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 vastly more represented than others; this allows LP methods to exhibit good results 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 the effectiveness and efficiency of 18 state-of-the-art methods, consider a rule-based baseline, and report detailed analysis over the most popular benchmarks in the literature.