Li Linfeng, Wang Peng, Wang Yao, Wang Shenghui, Yan Jun, Jiang Jinpeng, Tang Buzhou, Wang Chengliang, Liu Yuting
Institute of Information Science, Beijing Jiaotong University, Beijing, China.
Yidu Cloud Technology Inc, Beijing, China.
JMIR Med Inform. 2020 May 21;8(5):e17645. doi: 10.2196/17645.
Knowledge graph embedding is an effective semantic representation method for entities and relations in knowledge graphs. Several translation-based algorithms, including TransE, TransH, TransR, TransD, and TranSparse, have been proposed to learn effective embedding vectors from typical knowledge graphs in which the relations between head and tail entities are deterministic. However, in medical knowledge graphs, the relations between head and tail entities are inherently probabilistic. This difference introduces a challenge in embedding medical knowledge graphs.
We aimed to address the challenge of how to learn the probability values of triplets into representation vectors by making enhancements to existing TransX (where X is E, H, R, D, or Sparse) algorithms, including the following: (1) constructing a mapping function between the score value and the probability, and (2) introducing probability-based loss of triplets into the original margin-based loss function.
We performed the proposed PrTransX algorithm on a medical knowledge graph that we built from large-scale real-world electronic medical records data. We evaluated the embeddings using link prediction task.
Compared with the corresponding TransX algorithms, the proposed PrTransX performed better than the TransX model in all evaluation indicators, achieving a higher proportion of corrected entities ranked in the top 10 and normalized discounted cumulative gain of the top 10 predicted tail entities, and lower mean rank.
The proposed PrTransX successfully incorporated the uncertainty of the knowledge triplets into the embedding vectors.
知识图谱嵌入是一种用于知识图谱中实体和关系的有效语义表示方法。已经提出了几种基于翻译的算法，包括TransE、TransH、TransR、TransD和TranSparse，用于从典型知识图谱中学习有效的嵌入向量，其中头实体和尾实体之间的关系是确定性的。然而，在医学知识图谱中，头实体和尾实体之间的关系本质上是概率性的。这种差异给医学知识图谱的嵌入带来了挑战。
我们旨在通过对现有的TransX（其中X为E、H、R、D或Sparse）算法进行改进来应对如何将三元组的概率值学习到表示向量中的挑战，包括以下方面：（1）构建分数值与概率之间的映射函数，以及（2）将基于概率的三元组损失引入到原始的基于边际的损失函数中。
我们在从大规模真实世界电子病历数据构建的医学知识图谱上执行了所提出的PrTransX算法。我们使用链接预测任务评估嵌入。
与相应的TransX算法相比，所提出的PrTransX在所有评估指标上的表现均优于TransX模型，在前10个排名中正确实体的比例更高，前10个预测尾实体的归一化折损累计增益更高，平均排名更低。
所提出的PrTransX成功地将知识三元组的不确定性纳入到嵌入向量中。
