A multi-instance multi-label learning algorithm based on instance correlations

作     者：Liu, Chanjuan Chen, Tongtong Ding, Xinmiao Zou, Hailin Tong, Yan 

作者机构：Ludong Univ Sch Informat & Elect Engn Yantai 264025 Peoples R China Univ South Carolina Dept Comp Sci & Engn Columbia SC 29208 USA Shandong Inst Business & Technol Sch Informat & Elect Engn Yantai 264005 Peoples R China 

出 版 物：《MULTIMEDIA TOOLS AND APPLICATIONS》 (多媒体工具和应用)

年 卷 期：2016年第75卷第19期

页      面：12263-12284页

核心收录：

学科分类：0808[工学-电气工程] 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：National Science Foundation of China [61170161, 61300155, 61303086] Shandong Province Scholarship Council, Ph.D. Programs Foundation of Ludong University [LY2014033] 

主　　题：Multi-instance multi-label learning Multi-label classification Instance correlations Multiple-kernel fusion 

摘      要：Existing multi-instance multi-label learning algorithms generally assume that instances in a bag are independent of each other, which is difficult to be guaranteed in practical applications. A novel multi-instance multi-label learning algorithm is proposed by modeling instance correlations in each bag. First, instance correlations are introduced in multi-instance multi-label learning by constructing graphs. Then, different kernel matrices are derived from kernel functions based on graphs at different scales, which are employed to train Multiple Kernel Support Vector Machine (MKSVM) classifiers. Experimental results on different datasets show that the proposed method significantly improves the accuracy of the multi-label classification compared with the state-of-the-art methods.