arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.04868stat.MLcs.LG
收藏

知识图中链路预测的SimplE嵌入

SimplE Embedding for Link Prediction in Knowledge Graphs

University of British Columbia(不列颠哥伦比亚大学)

Seyed Mehran Kazemi, David Poole

摘要:

知识图谱包含关于世界的知识,并提供这些知识的结构化表示。目前的知识图谱只包含世界上真实知识的一小部分。链接预测方法的目标是在给定实体之间的现有链接的情况下预测知识图的新链接。张量分解方法已被证明是有前途的链接预测问题。在1927年提出的,典型的Polyadic(CP)分解是最早的张量分解方法之一。CP通常在链接预测方面表现不佳,因为它为每个实体学习两个独立的嵌入向量,而它们实际上是绑定的。我们提出了一个简单的增强CP(我们称之为SimpleE),让每个实体的两个嵌入学习依赖。SimpleE的复杂度随着嵌入的大小线性增长。通过SimpleE学习的嵌入是可解释的,某些类型的背景知识可以通过权重绑定并入这些嵌入。我们证明了SimplE是完全表达的,并推导出一个充分表达的嵌入大小的界限。我们的经验表明,尽管它的简单性,简单优于几个国家的最先进的张量因式分解技术。SimplE的代码可以在GitHub上找到,网址是https://github.com/Mehran-k/SimplE。

英文摘要:

Knowledge graphs contain knowledge about the world and provide a structured representation of this knowledge. Current knowledge graphs contain only a small subset of what is true in the world. Link prediction approaches aim at predicting new links for a knowledge graph given the existing links among the entities. Tensor factorization approaches have proved promising for such link prediction problems. Proposed in 1927, Canonical Polyadic (CP) decomposition is among the first tensor factorization approaches. CP generally performs poorly for link prediction as it learns two independent embedding vectors for each entity, whereas they are really tied. We present a simple enhancement of CP (which we call SimplE) to allow the two embeddings of each entity to be learned dependently. The complexity of SimplE grows linearly with the size of embeddings. The embeddings learned through SimplE are interpretable, and certain types of background knowledge can be incorporated into these embeddings through weight tying. We prove SimplE is fully expressive and derive a bound on the size of its embeddings for full expressivity. We show empirically that, despite its simplicity, SimplE outperforms several state-of-the-art tensor factorization techniques. SimplE's code is available on GitHub at https://github.com/Mehran-k/SimplE.

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。

↑