结合实体和关系消息传递的低资源知识图谱补全  

Low-Resource Knowledge Graph Completion by Combining Entity and Relation Message Passing

作　　者：张婷 杜方 宋丽娟 史英杰 赵国栋 李婷 ZHANG Ting;DU Fang;SONG Lijuan;SHI Yingjie;ZHAO Guodong;LI Ting(School of Information Engineering,Ningxia University,Yinchuan 750021,China;Beijing Institute of Fashion Technology,Beijing 100029,China;Network Information Management Center,Ningxia University,Yinchuan 750021,China;School of Mathematics and Statistics,Ningxia University,Yinchuan 750021,China)

机构地区：[1]宁夏大学信息工程学院,银川750021 [2]北京服装学院,北京100029 [3]宁夏大学网络与信息管理中心,银川750021 [4]宁夏大学数学统计学院,银川750021

出　　处：《计算机工程与应用》2024年第22期137-144,共8页Computer Engineering and Applications

基　　金：国家自然科学基金(62062058);宁夏自然科学基金(2021AAC03022,2021AAC03118)。

摘　　要：知识图谱补全是知识图谱领域的一个重要研究问题。现有的知识图谱补全工作大多假设在充足的三元组实例上进行,然而在医疗、法律等垂直领域,数据难以获取,缺乏足够的数据和先验知识,属于低资源场景。研究低资源场景下的知识图谱补全方法对于解决实际问题具有重要意义。提出结合节点和边消息传递的低资源知识图谱补全方法SMKGC(similarity messages knowledge graph completion),该方法通过感知局部关系(边)与实体(节点)实现对链接的预测。与现有方法不同,SMKGC将语义相似节点及语义相似边的特征信息与Pathcon模型进行融合,从而通过增强消息传递的特征表示来提升链接预测的准确性。具体包括两个模块:(1)基于实体相似的消息传递,在捕获给定实体对相邻实体的基础上,聚合周围相似实体信息;(2)基于关系相似的消息传递,通过关系路径获取给定实体对的相对位置,同时结合路径的相似边实现关系预测。实验结果表明,该方法在知识图谱常用的基准数据集上明显优于其他方法,同时也证明了结合相似实体和关系消息传递在低资源知识图谱补全任务中可以有效提升预测的准确度。Knowledge graph completion is a significant research topic in knowledge graphs.Most existing work assumes that it is carried out on sufficient triadic instances.However,in vertical areas such as medicine and law,data are difficult to obtain,and they may belong to low-resource scenarios due to the lack of adequate data and prior knowledge.Therefore,studying knowledge graph completion methods in low-resource scenarios is crucial for solving practical problems.This paper proposes a low-resource knowledge graph completion method SMKGC(similarity messages knowledge graph com-pletion),which combines nodes and edges message passing to predict links by sensing local relations and entities.Different with existing methods,SMKGC fuses the feature information of semantically similar nodes and semantically parallel edges with the Pathcon model,thereby to enhance the feature representation of message passing and improve link predic-tion accuracy.Specifically,it includes two modules:(1)Entity-similarity-based messaging,which aggregates information surrounding similar entities on the basis of capturing the neighboring edges of a given entity pair.(2)Relation-similarity-based messaging,which obtains the relative positions of a given entity pair through relational paths and combines the simi-lar edges of the paths to perform relational prediction.Experimental results demonstrate that this method significantly out-performs other methods on benchmark datasets commonly used in knowledge graphs.The results also show that similar entities and relation messaging based on similar nodes can improve prediction accuracy in low-resource knowledge graph completion tasks.

关 键 词：知识图谱 相似性 链接预测 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]