TransINT：在具有线性子空间同构交的知识图谱中嵌入蕴涵规则
TransINT: Embedding Implication Rules in Knowledge Graphs with Isomorphic Intersections of Linear Subspaces
摘要：
知识图谱（KG）由实体和关系组成，提供知识的结构化表示。为了便于访问关系数据的统计方法，已经引入了将KG嵌入f（KG）$\in$ R^d的多种方法。我们提出了TransINT，一种新颖的和可解释的KG嵌入方法，同构地保留了嵌入空间中的关系之间的隐含顺序。给定蕴涵规则，TransINT将实体集（由关系绑定）映射到连续向量集，这些向量集与关系蕴涵同构地包含排序。通过一种新的参数共享方案，TransINT可以在没有规则基础的情况下对缺失但隐含的事实进行自动训练。在一个基准数据集上，我们在链接预测和三重分类中的表现优于现有最先进的规则集成嵌入方法。TransINT所嵌入的连续集合之间的角度为挖掘关系之间的语义相关性和蕴涵规则提供了一种可解释的方法。
英文摘要：
Knowledge Graphs (KG), composed of entities and relations, provide a structured representation of knowledge. For easy access to statistical approaches on relational data, multiple methods to embed a KG into f(KG) $\in$ R^d have been introduced. We propose TransINT, a novel and interpretable KG embedding method that isomorphically preserves the implication ordering among relations in the embedding space. Given implication rules, TransINT maps set of entities (tied by a relation) to continuous sets of vectors that are inclusion-ordered isomorphically to relation implications. With a novel parameter sharing scheme, TransINT enables automatic training on missing but implied facts without rule grounding. On a benchmark dataset, we outperform the best existing state-of-the-art rule integration embedding methods with significant margins in link Prediction and triple Classification. The angles between the continuous sets embedded by TransINT provide an interpretable way to mine semantic relatedness and implication rules among relations.
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。
