A label noise filtering and label missing supplement framework based on game theory

作     者：Yuwen Liu Rongju Yao Song Jia Fan Wang Ruili Wang Rui Ma Lianyong Qi Yuwen Liu;Rongju Yao;Song Jia;Fan Wang;Ruili Wang;Rui Ma;Lianyong Qi

作者机构：College of Computer Science and TechnologyChina University of Petroleum(East China)Qingdao 266580China Weifang Key Laboratory of Blockchain on Agricultural VegetablesWeifang University of Science and TechnologyShouguangChina China Unicom Taian BranchChina School of Natural and Computational SciencesMassey UniversityNew Zealand General Education DepartmentShandong First Medical UniversityShandong Academy of Medical SciencesTai'an271000China College of Computer Science and TechnologyZhejiang UniversityHangzhouChina 

出 版 物：《Digital Communications and Networks》 (数字通信与网络（英文版）)

年 卷 期：2023年第9卷第4期

页      面：887-895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：supported by the National Natural Science Foundation of China(No.61872219) the Natural Science Foundation of Shandong Province(ZR2019MF001) 

主　　题：Label noise FastText Cosine similarity Game theory LSTM 

摘      要：Labeled data is widely used in various classification ***,there is a huge challenge that labels are often added *** labels added by malicious users will affect the training effect of the *** unreliability of labeled data has hindered the *** order to solve the above problems,we propose a framework of Label Noise Filtering and Missing Label Supplement(LNFS).And we take location labels in Location-Based Social Networks(LBSN)as an example to implement our *** the problem of label noise filtering,we first use FastText to transform the restaurant s labels into vectors,and then based on the assumption that the label most similar to all other labels in the location is most *** use cosine similarity to judge and select the most representative *** the problem of label missing,we use simple common word similarity to judge the similarity of users comments,and then use the label of the similar restaurant to supplement the missing *** optimize the performance of the model,we introduce game theory into our model to simulate the game between the malicious users and the model to improve the reliability of the ***,a case study is given to illustrate the effectiveness and reliability of LNFS.