Embedding-based approximate query for knowledge graph  

基于嵌入的知识图谱近似查询

作　　者：Qiu Jingyi Zhang Duxi Song Aibo Wang Honglin Zhang Tianbo Jin Jiahui Fang Xiaolin Li Yaqi 邱敬怡;章杜锡;宋爱波;王红林;张添博;金嘉晖;方效林;李雅琦(东南大学计算机科学与工程学院,南京211189;国网浙江省电力有限公司宁波供电公司,宁波315000;南京信息工程大学人工智能学院,南京210044)

机构地区：[1]School of Computer Science and Engineering,Southeast University,Nanjing 211189,China [2]Ningbo Power Supply Co.,State Grid Zhejiang Electric Power Co.,Ltd.,Ningbo 315000,China [3]School of Artificial Intelligence,Nanjing University of Information Science and Technology,Nanjing 210044,China

出　　处：《Journal of Southeast University(English Edition)》2024年第4期417-424,共8页东南大学学报（英文版）

基　　金：The State Grid Technology Project(No.5108202340042A-1-1-ZN).

摘　　要：To solve the low efficiency of approximate queries caused by the large sizes of the knowledge graphs in the real world,an embedding-based approximate query method is proposed.First,the nodes in the query graph are classified according to the degrees of approximation required for different types of nodes.This classification transforms the query problem into three constraints,from which approximate information is extracted.Second,candidates are generated by calculating the similarity between embeddings.Finally,a deep neural network model is designed,incorporating a loss function based on the high-dimensional ellipsoidal diffusion distance.This model identifies the distance between nodes using their embeddings and constructs a score function.k nodes are returned as the query results.The results show that the proposed method can return both exact results and approximate matching results.On datasets DBLP(DataBase systems and Logic Programming)and FUA-S(Flight USA Airports-Sparse),this method exhibits superior performance in terms of precision and recall,returning results in 0.10 and 0.03 s,respectively.This indicates greater efficiency compared to PathSim and other comparative methods.为解决现实生活中知识图谱规模庞大而导致近似查询效率低下的问题,提出了一种基于嵌入的知识图谱近似查询方法.首先对查询图中的节点进行分类,根据不同类型节点所需的近似程度,将查询问题转化为3个约束条件,提取近似信息.然后,通过计算嵌入之间的相似度,生成候选集.最后,设计了一个深度神经网络模型和基于高维椭球形扩散距离的损失函数,根据嵌入判断节点间距离,并构建打分函数,返回k个节点作为查询结果.结果表明,所提方法可以同时返回精确匹配结果和近似匹配结果.该方法在DBLP和FUA-S两个数据集上均获得了最高的准确率和召回率,且可分别在0.10和0.03 s内返回结果,效率高于PathSim等对比方法.

关 键 词：approximate query knowledge graph EMBEDDING deep neural network 

分 类 号：TP392[自动化与计算机技术—计算机应用技术]