Multi-label learning algorithm with SVM based association  

作　　者：Feng Pan Qin Danyang Ji Ping Ma Jingya Zhang Yan Yang Songxiang 冯攀;Qin Danyang;Ji Ping;Ma Jingya;Zhang Yan;Yang Songxiang(Key Laboratory of Electronic and Communication Engineering,Heilongjiang University;School of Electronics and Information Engineering,Harbin Institute of Technology)

机构地区：[1]Key Laboratory of Electronic and Communication Engineering,Heilongjiang University [2]School of Electronics and Information Engineering,Harbin Institute of Technology

出　　处：《High Technology Letters》2019年第1期97-104,共8页高技术通讯（英文版）

基　　金：Support by the National High Technology Research and Development Program of China(No.2012AA120802);National Natural Science Foundation of China(No.61771186);Postdoctoral Research Project of Heilongjiang Province(No.LBH-Q15121);Undergraduate University Project of Young Scientist Creative Talent of Heilongjiang Province(No.UNPYSCT-2017125)

摘　　要：Multi-label learning is an active research area which plays an important role in machine learning. Traditional learning algorithms, however, have to depend on samples with complete labels. The existing learning algorithms with missing labels do not consider the relevance of labels, resulting in label estimation errors of new samples. A new multi-label learning algorithm with support vector machine(SVM) based association(SVMA) is proposed to estimate missing labels by constructing the association between different labels. SVMA will establish a mapping function to minimize the number of samples in the margin while ensuring the margin large enough as well as minimizing the misclassification probability. To evaluate the performance of SVMA in the condition of missing labels, four typical data sets are adopted with the integrity of the labels being handled manually. Simulation results show the superiority of SVMA in dealing with the samples with missing labels compared with other models in image classification.Multi-label learning is an active research area which plays an important role in machine learning. Traditional learning algorithms, however, have to depend on samples with complete labels. The existing learning algorithms with missing labels do not consider the relevance of labels, resulting in label estimation errors of new samples. A new multi-label learning algorithm with support vector machine(SVM) based association(SVMA) is proposed to estimate missing labels by constructing the association between different labels. SVMA will establish a mapping function to minimize the number of samples in the margin while ensuring the margin large enough as well as minimizing the misclassification probability. To evaluate the performance of SVMA in the condition of missing labels, four typical data sets are adopted with the integrity of the labels being handled manually. Simulation results show the superiority of SVMA in dealing with the samples with missing labels compared with other models in image classification.

关 键 词：multi-label learning missing labels ASSOCIATION support vector machine(SVM) 

分 类 号：N[自然科学总论]