arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.07130cs.LG
收藏

STaR:基于缩放、平移和旋转的知识图谱嵌入

STaR: Knowledge Graph Embedding by Scaling, Translation and Rotation

Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院)

Jiayi Li, Yujiu Yang

摘要:

双线性方法是知识图谱嵌入中的主流方法,其目的是学习知识图谱中实体和关系的低维表示,并完成缺失的环节。大多数现有的工作是找到关系之间的模式,并有效地建模,以完成这一任务。前人的工作主要发现了非对易性等6种重要的模式。尽管一些双线性方法成功地对这些模式进行了建模,但它们忽略了并发处理1对N、N对1和N对N关系(或复杂关系),这损害了它们的表达能力。为此,我们集成缩放,平移和旋转的组合,可以解决复杂的关系和模式,分别,缩放是投影的简化。因此,我们提出了由上述两部分组成的相应的双线性模型缩放平移和旋转(STaR)。此外,由于平移不能直接结合到双线性模型中,我们引入平移矩阵作为等价物。理论分析证明STaR能够同时对所有模式进行建模并处理复杂关系,实验证明了STaR在常用的链接预测基准测试上的有效性。

英文摘要:

The bilinear method is mainstream in Knowledge Graph Embedding (KGE), aiming to learn low-dimensional representations for entities and relations in Knowledge Graph (KG) and complete missing links. Most of the existing works are to find patterns between relationships and effectively model them to accomplish this task. Previous works have mainly discovered 6 important patterns like non-commutativity. Although some bilinear methods succeed in modeling these patterns, they neglect to handle 1-to-N, N-to-1, and N-to-N relations (or complex relations) concurrently, which hurts their expressiveness. To this end, we integrate scaling, the combination of translation and rotation that can solve complex relations and patterns, respectively, where scaling is a simplification of projection. Therefore, we propose a corresponding bilinear model Scaling Translation and Rotation (STaR) consisting of the above two parts. Besides, since translation cannot be incorporated into the bilinear model directly, we introduce translation matrix as the equivalent. Theoretical analysis proves that STaR is capable of modeling all patterns and handling complex relations simultaneously, and experiments demonstrate its effectiveness on commonly used benchmarks for link prediction.

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。

↑