论文标题
伪 - 利曼式嵌入模型，用于多关系图表
Pseudo-Riemannian Embedding Models for Multi-Relational Graph Representations
论文作者
论文摘要
在本文中，我们将单连接伪式图嵌入模型概括为多关系网络，并表明将关系的典型方法作为流动转换，从riemannian转化为伪里曼尼亚人的情况。此外，我们将关系视为多时间歧管的独立时空子曼群，并考虑伪里曼式嵌入模型与其wick-Rot的Riemannian对应物之间的插值。我们在链接预测的任务中验证了这些扩展，重点是洛伦兹歧管，并证明了它们在知识图完成和在生物领域中的知识发现中的使用。
In this paper we generalize single-relation pseudo-Riemannian graph embedding models to multi-relational networks, and show that the typical approach of encoding relations as manifold transformations translates from the Riemannian to the pseudo-Riemannian case. In addition we construct a view of relations as separate spacetime submanifolds of multi-time manifolds, and consider an interpolation between a pseudo-Riemannian embedding model and its Wick-rotated Riemannian counterpart. We validate these extensions in the task of link prediction, focusing on flat Lorentzian manifolds, and demonstrate their use in both knowledge graph completion and knowledge discovery in a biological domain.
