HGE：在异构几何子空间乘积空间中嵌入时序知识图谱
HGE: Embedding Temporal Knowledge Graphs in a Product Space of Heterogeneous Geometric Subspaces
AI总结：
针对时序知识图谱嵌入受限于单一几何空间的问题，提出将事实映射到复、对偶及分裂复空间乘积空间的HGE方法，并引入时序几何注意力机制，在标准基准上超越现有模型。
摘要：
时序知识图谱表示时序事实 $(s,p,o,τ)$，该事实通过关系标签 $p$ 在时间 $τ$ 处关联主体 $s$ 和客体 $o$，其中 $τ$ 可以是时间点或时间区间。时序知识图谱可能在不同时间点表现出静态时序模式，并在不同时间戳之间表现出动态时序模式。为了学习丰富的静态和动态时序模式并将其应用于推理，文献中已提出了多种嵌入方法。然而，由于大多数方法依赖于单一的底层嵌入空间，它们建模所有类型时序模式的能力受到严重限制，因为必须遵循其单一嵌入空间的几何性质。我们通过一种将时序事实映射到多个具有不同几何性质的异构几何子空间（即复空间、对偶空间和分裂复空间）的乘积空间中的嵌入方法来消除这一限制。此外，我们提出了一种时序几何注意力机制，以便根据捕获的关系和时序信息方便地整合来自不同几何子空间的信息。在标准时序基准数据集上的实验结果表明，我们的方法优于最先进的模型。
英文摘要：
Temporal knowledge graphs represent temporal facts $(s,p,o,τ)$ relating a subject $s$ and an object $o$ via a relation label $p$ at time $τ$, where $τ$ could be a time point or time interval. Temporal knowledge graphs may exhibit static temporal patterns at distinct points in time and dynamic temporal patterns between different timestamps. In order to learn a rich set of static and dynamic temporal patterns and apply them for inference, several embedding approaches have been suggested in the literature. However, as most of them resort to single underlying embedding spaces, their capability to model all kinds of temporal patterns was severely limited by having to adhere to the geometric property of their one embedding space. We lift this limitation by an embedding approach that maps temporal facts into a product space of several heterogeneous geometric subspaces with distinct geometric properties, i.e.\ Complex, Dual, and Split-complex spaces. In addition, we propose a temporal-geometric attention mechanism to integrate information from different geometric subspaces conveniently according to the captured relational and temporal information. Experimental results on standard temporal benchmark datasets favorably evaluate our approach against state-of-the-art models.
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。
