In recent years, knowledge graph completion methods have been extensively studied, in which graph embedding approaches learn low dimensional representations of entities and relations to predict missing facts. Those models usually view the relation vector as a translation (TransE) or rotation (rotatE and QuatE) between entity pairs, enjoying the advantage of simplicity and efficiency. However, QuatE has two main problems: 1) The model to capture the ability of representation and feature interaction between entities and relations are relatively weak because it only relies on the rigorous calculation of three embedding vectors; 2) Although the model can handle various relation patterns including symmetry, anti-symmetry, inversion and composition, but mapping properties of relations are not to be considered, such as one-to-many, many-to-one, and many-to-many. In this paper, we propose a novel model, QuatDE, with a dynamic mapping strategy to explicitly capture a variety of relational patterns, enhancing the feature interaction capability between elements of the triplet. Our model relies on three extra vectors donated as subject transfer vector, object transfer vector and relation transfer vector. The mapping strategy dynamically selects the transition vectors associated with each triplet, used to adjust the point position of the entity embedding vectors in the quaternion space via Hamilton product. Experiment results show QuatDE achieves state-of-the-art performance on three well-established knowledge graph completion benchmarks. In particular, the MR evaluation has relatively increased by 26% on WN18 and 15% on WN18RR, which proves the generalization of QuatDE.


翻译:近年来,对知识图完成方法进行了广泛研究,在这种方法中,嵌入图的方法学习了实体和关系的低维度表达方式,以预测缺失的事实。这些模型通常将关系矢量视为实体对对口之间的翻译(TransE)或轮换(rotatE和 QuatE),享有简单和效率的优势。然而,QuatE有两个主要问题:1) 收集实体和关系之间代表性和特征互动能力的模型相对薄弱,因为它仅依赖于严格计算三个嵌入矢量的精确度;2) 尽管模型可以处理各种关系模式,包括对称、反对称、改变和构成,但关系映射属性不考虑,例如一对一对一、多对一和多对一和多对一。 但是,在本文件中,我们提出了一个新的模型,即 QuatDE, 并有一个动态映射战略,以明确反映各种关联模式,加强三重矢量的特性互动能力。我们的模型依赖于作为对象转移矢量对象捐赠的三个额外矢量模式,DE对矢量的转移和组成,但不能考虑关系属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性和属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性属性和属性, ; ; ; ; ; ; ; 和属性矩阵矩阵矩阵值,在每一级级矢量上,在不断演演算式战略中,在不断演进度上,在Smaxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

3
下载
关闭预览

相关内容

17篇知识图谱Knowledge Graphs论文 @AAAI2020
专知会员服务
167+阅读 · 2020年2月13日
已删除
将门创投
7+阅读 · 2019年10月10日
Query Embedding on Hyper-relational Knowledge Graphs
Arxiv
4+阅读 · 2021年6月17日
Efficiently Embedding Dynamic Knowledge Graphs
Arxiv
14+阅读 · 2019年10月15日
Arxiv
4+阅读 · 2018年11月26日
Arxiv
9+阅读 · 2018年10月18日
Arxiv
7+阅读 · 2018年3月21日
VIP会员
相关VIP内容
相关资讯
已删除
将门创投
7+阅读 · 2019年10月10日
Top
微信扫码咨询专知VIP会员