论文标题
密集：具有自适应语义层次结构的知识图的增强的非交通性表示
DensE: An Enhanced Non-commutative Representation for Knowledge Graph Embedding with Adaptive Semantic Hierarchy
论文作者
论文摘要
捕获关系的组成模式是知识图完成中的重要任务。它也是迈向多跳推理的基本一步。以前，已经开发了几种基于旋转的转换方法，以使用一系列复杂值对角矩阵的乘积建模复合关系。但是，这些方法倾向于对综合关系做出几个过分简化的假设，例如，迫使它们是可交换的，独立于实体和缺乏语义层次结构。为了系统地解决这些问题，我们开发了一种新颖的知识嵌入方法，名为“密集”，为复杂的关系模式提供了改进的建模方案。特别是，我们的方法将每个关系分解为SO（3）基于组的旋转操作员和缩放操作员在三维（3-D）欧几里得空间中。该设计原理带来了我们方法的几个优点：（1）对于综合关系，相应的对角线关系矩阵可能是非共同的，这反映了现实世界应用中的主要情况； （2）我们的模型保留了关系操作与实体嵌入之间的自然相互作用； （3）缩放操作为实体的内在语义层次结构提供了建模能力； （4）在参数大小和训练时间方面，通过高计算效率实现了致密的增强表现； （5）在欧几里得空间中而不是四元空间中建模实体，这是对关系模式的直接几何解释。多个基准知识图上的实验结果表明，密集的表现优于缺少链路预测的当前最新模型，尤其是在复合关系上。
Capturing the composition patterns of relations is a vital task in knowledge graph completion. It also serves as a fundamental step towards multi-hop reasoning over learned knowledge. Previously, several rotation-based translational methods have been developed to model composite relations using the product of a series of complex-valued diagonal matrices. However, these methods tend to make several oversimplified assumptions on the composite relations, e.g., forcing them to be commutative, independent from entities and lacking semantic hierarchy. To systematically tackle these problems, we have developed a novel knowledge graph embedding method, named DensE, to provide an improved modeling scheme for the complex composition patterns of relations. In particular, our method decomposes each relation into an SO(3) group-based rotation operator and a scaling operator in the three dimensional (3-D) Euclidean space. This design principle leads to several advantages of our method: (1) For composite relations, the corresponding diagonal relation matrices can be non-commutative, reflecting a predominant scenario in real world applications; (2) Our model preserves the natural interaction between relational operations and entity embeddings; (3) The scaling operation provides the modeling power for the intrinsic semantic hierarchical structure of entities; (4) The enhanced expressiveness of DensE is achieved with high computational efficiency in terms of both parameter size and training time; and (5) Modeling entities in Euclidean space instead of quaternion space keeps the direct geometrical interpretations of relational patterns. Experimental results on multiple benchmark knowledge graphs show that DensE outperforms the current state-of-the-art models for missing link prediction, especially on composite relations.
