基于循环一致性损失的知识图谱嵌入的研究

作     者：李迦龙 郭中华 蔺金元 

作者机构：宁夏大学物理与电子电气工程学院宁夏 银川 

出 版 物：《人工智能与机器人研究》 (Artificial Intelligence and Robotics Research)

年 卷 期：2024年第13卷第4期

页      码：822-836页

摘      要：基于生成对抗网络中的循环一致性原则,提出了一个基于循环一致性损失的知识图谱嵌入模型。该模型首先使用ConvE模型利用头实体和关系构造的“图片”对尾实体进行预测,再利用尾实体和关系构造的“逆图片”对头实体进行预测。同时根据循环一致性原理,构造了ConvE模型的一个新的损失函数,解决了网络的可逆性。在WN18、FB15k以及YAGO3-10三个数据集上设计实验,证明了模型有效地缩短了头实体和原头实体的语义空间距离。Based on the cyclic consistency principle in generative adversarial networks, a knowledge graph embedding model based on cyclic consistency loss is proposed. Firstly, the ConvE model is used to predict the tail entity by using the “picture” constructed by the head entity and the relationship, and then the “inverse picture” constructed by the tail entity and the relationship is used to predict the head entity. According to the principle of cyclic consistency, a new loss function of ConvE model is constructed to solve the reversibility of the network. Experiments are designed on WN18, FB15k and YAGO3-10 data sets, and it is proved that the model can effectively shorten the semantic space distance between the header entity and the original header entity.

主 题 词：知识图谱 TransE ConvE 循环一致性 

学科分类：08[工学] 0812[工学-测绘类] 

D　O　I：10.12677/airr.2024.134085

馆 藏 号：203155671...