用双向旋转与距离自适应提升知识图谱嵌入效果
Distance-Adaptive Quaternion Knowledge Graph Embedding with Bidirectional Rotation
- 通过头尾实体双向旋转学习语义特征
- 引入距离自适应翻译建模实体间几何关系
- 数学证明可处理复杂逻辑关系，适合知识推理任务
四元数包含一个实部和三个虚部，为知识图谱学习提供了更具表现力的超复数空间。现有四元数嵌入模型通过语义匹配或几何距离评分函数衡量三元组合理性，但语义匹配会降低实体可分性，而距离评分函数又削弱了实体语义。为此，我们提出一种新型四元数知识图谱嵌入模型，将语义匹配与实体几何距离结合以更准确评估三元组可信度。具体地，在四元数空间中，对头实体执行右旋转，对尾实体执行逆旋转，以学习丰富语义特征；同时采用距离自适应平移建模实体间的几何距离。此外，我们提供数学证明表明该模型能有效处理复杂逻辑关系。大量实验结果与分析显示，本模型在知名知识图谱补全基准数据集上显著优于先前方法。代码已开源：https://github.com/llqy123/DaBR。
原文摘要 · Abstract (English)
Quaternion contains one real part and three imaginary parts, which provided a more expressive hypercomplex space for learning knowledge graph. Existing quaternion embedding models measure the plausibility of a triplet either through semantic matching or geometric distance scoring functions. However, it appears that semantic matching diminishes the separability of entities, while the distance scoring function weakens the semantics of entities. To address this issue, we propose a novel quaternion knowledge graph embedding model. Our model combines semantic matching with entity's geometric distance to better measure the plausibility of triplets. Specifically, in the quaternion space, we perform a right rotation on head entity and a reverse rotation on tail entity to learn rich semantic features. Then, we utilize distance adaptive translations to learn geometric distance between entities. Furthermore, we provide mathematical proofs to demonstrate our model can handle complex logical relationships. Extensive experimental results and analyses show our model significantly outperforms previous models on well-known knowledge graph completion benchmark datasets. Our code is available at https://github.com/llqy123/DaBR.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。