论文标题
低维屈曲知识图嵌入
Low-Dimensional Hyperbolic Knowledge Graph Embeddings
论文作者
论文摘要
知识图（kg）嵌入学习实体和关系的低维表示，以预测缺失的事实。 KG通常表现出必须保留在嵌入空间中的层次和逻辑模式。对于层次数据，双曲线嵌入方法显示出对高保真性和简约表示的希望。但是，现有的双曲线嵌入方法不能说明kg中丰富的逻辑模式。在这项工作中，我们介绍了一类双曲KG嵌入模型，这些模型同时捕获了层次结构和逻辑模式。我们的方法将双曲线反射和旋转与对模型复杂关系模式的关注相结合。标准KG基准的实验结果表明，我们的方法对以前的欧几里得和双曲线的努力在低维度的平均互惠等级（MRR）中提高了6.1％。此外，我们观察到，不同的几何变换捕获了不同类型的关系，而基于注意力的转换则推广到多个关系。在高维度中，我们的方法在WN18RR上产生了49.6％的最新MRR，而Yago3-10的最先进MRR为57.7％。
Knowledge graph (KG) embeddings learn low-dimensional representations of entities and relations to predict missing facts. KGs often exhibit hierarchical and logical patterns which must be preserved in the embedding space. For hierarchical data, hyperbolic embedding methods have shown promise for high-fidelity and parsimonious representations. However, existing hyperbolic embedding methods do not account for the rich logical patterns in KGs. In this work, we introduce a class of hyperbolic KG embedding models that simultaneously capture hierarchical and logical patterns. Our approach combines hyperbolic reflections and rotations with attention to model complex relational patterns. Experimental results on standard KG benchmarks show that our method improves over previous Euclidean- and hyperbolic-based efforts by up to 6.1% in mean reciprocal rank (MRR) in low dimensions. Furthermore, we observe that different geometric transformations capture different types of relations while attention-based transformations generalize to multiple relations. In high dimensions, our approach yields new state-of-the-art MRRs of 49.6% on WN18RR and 57.7% on YAGO3-10.
