NagE: Non-Abelian Group Embedding for Knowledge Graphs
NagE: Non-Abelian Group Embedding for Knowledge Graphs
复制标题
DOI：
10.1145/3340531.3411875
复制
发表时间：
2020-05
期刊：
影响因子：
--
通讯作者：
Tong Yang;Long Sha;Pengyu Hong
中科院分区：
文献类型：
--
作者：
Tong Yang;Long Sha;Pengyu Hong
我们证明了隐藏在关系知识嵌入问题中的群代数结构的存在，这表明基于群的嵌入框架对于设计嵌入模型是必不可少的。我们的理论分析只是探讨嵌入问题本身的内在属性，因此是模型无关的。在理论分析的基础上，提出了一种基于群论的知识图嵌入框架，将关系嵌入为群元素，实体用群动作空间中的向量表示。我们提供了一个通用的配方来构建嵌入模型与两个实例化的例子：SO3E和SU2E，这两个应用连续的非阿贝尔群作为关系嵌入。使用这两个示例模型的实证实验在基准数据集上显示了最先进的结果。
We demonstrated the existence of a group algebraic structure hidden in relational knowledge embedding problems, which suggests that a group-based embedding framework is essential for designing embedding models. Our theoretical analysis explores merely the intrinsic property of the embedding problem itself hence is model independent. Motivated by the theoretical analysis, we have proposed a group theory-based knowledge graph embedding framework, in which relations are embedded as group elements, and entities are represented by vectors in group action spaces. We provide a generic recipe to construct embedding models associated with two instantiating examples: SO3E and SU2E, both of which apply a continuous non-Abelian group as the relation embedding. Empirical experiments using these two exampling models have shown state-of-the-art results on benchmark datasets.