Learnability of multi-instance multi-label learning  

作　　者：WANG Wei ZHOU ZhiHua 

机构地区：[1]National Key Laboratory for Novel Softwaye Technology,Nanjing University,Nanjing 210046,China

出　　处：《Chinese Science Bulletin》2012年第19期2488-2491,共4页

基　　金：supported by the National Basic Research Program of China(2010CB327903);the National Natural Science Foundation of China(61073097,61021062)

摘　　要：Multi-instance multi-label learning(MIML) is a new machine learning framework where one data object is described by multiple instances and associated with multiple class labels.During the past few years,many MIML algorithms have been developed and many applications have been described.However,there lacks theoretical exploration to the learnability of MIML.In this paper,through proving a generalization bound for multi-instance single-label learner and viewing MIML as a number of multi-instance single-label learning subtasks with the correlation among the labels,we show that the MIML hypothesis class constructed from a multi-instance single-label hypothesis class is PAC-learnable.Multi-instance multi-label learning （MIML） is a new machine learning framework where one data object is described by multiple instances and associated with multiple class labels. During the past few years, many MIML algorithms have been developed and many applications have been described. However, there lacks theoretical exploration to the learnability of MIML. In this paper, through proving a generalization bound for multi-instance single-label learner and viewing MIML as a number of multi-instance single-label learning subtasks with the correlation among the labels, we show that the M1ML hypothesis class constructed from a multi-instance single-label hypothesis class is PAC-learnable.

关 键 词：机器学习 多实例 标签 易学 数据对象 ML算法 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]