Embedding-based approximate query for knowledge graph

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

作者机构：School of Computer Science and EngineeringSoutheast UniversityNanjing 211189China Ningbo Power Supply Co.State Grid Zhejiang Electric Power Co.Ltd.Ningbo 315000China School of Artificial IntelligenceNanjing University of Information Science and TechnologyNanjing 210044China 

出 版 物：《Journal of Southeast University(English Edition)》 (东南大学学报（英文版）)

年 卷 期：2024年第40卷第4期

页      面：417-424页

核心收录：

学科分类：081203[工学-计算机应用技术] 08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

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

主　　题：approximate query knowledge graph embedding deep neural network 

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 ***,the nodes in the query graph are classified according to the degrees of approximation required for different types of *** classification transforms the query problem into three constraints,from which approximate information is ***,candidates are generated by calculating the similarity between ***,a deep neural network model is designed,incorporating a loss function based on the high-dimensional ellipsoidal diffusion *** model identifies the distance between nodes using their embeddings and constructs a score function.k nodes are returned as the query *** results show that the proposed method can return both exact results and approximate matching *** 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,*** indicates greater efficiency compared to PathSim and other comparative methods.