Knowledge graph embedding transforms knowledge graphs into a continuous,
low-dimensional space, facilitating inference and completion tasks. This field
is mainly divided into translational distance models and semantic matching
models. A key challenge in translational distance models is their inability to
effectively differentiate between 'head' and 'tail' entities in graphs. To
address this, the novel location-sensitive embedding (LSE) method has been
developed. LSE innovatively modifies the head entity using relation-specific
mappings, conceptualizing relations as linear transformations rather than mere
translations. The theoretical foundations of LSE, including its
representational capabilities and its connections to existing models, have been
thoroughly examined. A more streamlined variant, LSEd, employs a diagonal
matrix for transformations to enhance practical efficiency. In tests conducted
on four large-scale datasets for link prediction, LSEd either outperforms or is
competitive with leading contemporary models.

知识图谱嵌入主要分为平移距离模型和语义匹配模型，在平移距离模型中，头尾实体的区分能力是一个关键挑战，而新颖的位置敏感嵌入 (LSE) 方法通过使用关系特定的映射来改变头实体，将关系概念化为线性变换，而不是简单的平移，它的理论基础、表现能力和与现有模型的联系都得到了充分的研究，一个更简化的变体 LSEd 通过对变换使用对角线矩阵以提高实际效率，在四个大规模数据集上进行的链接预测测试中，LSEd 要么表现出色，要么与领先的现代模型竞争力相当。