论文标题
低维度链接预测的双曲线分层知识图嵌入
Hyperbolic Hierarchical Knowledge Graph Embeddings for Link Prediction in Low Dimensions
论文作者
论文摘要
知识图嵌入（KGE）已被验证为有力的方法，用于推断知识图（kgs）中缺少链接的方法，它们通常将实体映射到欧几里得空间中，并将关系视为实体的转换。最近，一些Euclidean KGE方法已增强，以建模KGS中常见的语义层次结构，从而提高了链接预测的性能。为了嵌入层次数据，双曲线空间已成为传统欧几里得空间的有前途替代方案，提供了高忠诚度和较低的记忆消耗。与欧几里得不同，双曲线空间可供选择。但是，现有双曲线KGE方法很难手动获得最佳的曲率设置，从而限制了它们有效建模语义层次结构的能力。为了解决此限制，我们提出了一种新颖的KGE模型，称为$ \ textbf {hyt} $ erbolic $ \ textbf {h} $ ierarchical $ \ textbf {kge} $（hyphkge）。该模型引入了基于注意力的曲线，用于双曲线空间，这有助于保留丰富的语义层次结构。此外，为了利用保留的层次结构来推断缺失的链接，我们根据双曲线几何理论定义双曲线分层转换，包括层间和级别内建模。实验证明了在三个基准数据集（WN18RR，FB15K-237和Yago3-10）上提出的HIPHKGE模型的有效性。源代码将在https://github.com/wjzheng96/hyphkge上公开发布。
Knowledge graph embeddings (KGE) have been validated as powerful methods for inferring missing links in knowledge graphs (KGs) that they typically map entities into Euclidean space and treat relations as transformations of entities. Recently, some Euclidean KGE methods have been enhanced to model semantic hierarchies commonly found in KGs, improving the performance of link prediction. To embed hierarchical data, hyperbolic space has emerged as a promising alternative to traditional Euclidean space, offering high fidelity and lower memory consumption. Unlike Euclidean, hyperbolic space provides countless curvatures to choose from. However, it is difficult for existing hyperbolic KGE methods to obtain the optimal curvature settings manually, thereby limiting their ability to effectively model semantic hierarchies. To address this limitation, we propose a novel KGE model called $\textbf{Hyp}$erbolic $\textbf{H}$ierarchical $\textbf{KGE}$ (HypHKGE). This model introduces attention-based learnable curvatures for hyperbolic space, which helps preserve rich semantic hierarchies. Furthermore, to utilize the preserved hierarchies for inferring missing links, we define hyperbolic hierarchical transformations based on the theory of hyperbolic geometry, including both inter-level and intra-level modeling. Experiments demonstrate the effectiveness of the proposed HypHKGE model on the three benchmark datasets (WN18RR, FB15K-237, and YAGO3-10). The source code will be publicly released at https://github.com/wjzheng96/HypHKGE.
