不平衡数据的迁移学习分类算法  

Transfer Learning for Classification on Unbalanced Data

作　　者：陈琼[1] 徐洋洋 陈林清 CHEN Qiong;XU Yangyang;CHEN Linqing(School of Computer Science and Engineering,South China University of Technology,Guangzhou 510006,Guangdong,China)

机构地区：[1]华南理工大学计算机科学与工程学院,广东广州510006

出　　处：《华南理工大学学报（自然科学版）》2018年第1期122-130,共9页Journal of South China University of Technology(Natural Science Edition)

基　　金：国家自然科学基金资助项目(61573145);广东省自然科学基金资助项目(2015A030308018)~~

摘　　要：以Tr Adaboost算法为基础,提出了一个针对不平衡数据的二分类迁移学习算法Unbalanced Tr Adaboost(UBTA).UBTA算法利用不同类别的Precision-Recall曲线下的面积auprc(the Area Under the Precision-Recall Curve)计算弱分类器权重,对不同类别的样本采取不同的权重更新策略;AUC指标对数据分布变化不敏感,结合G-mean和BER能更准确地评估不平衡分类算法的性能.实验结果表明,UBTA具有较好的分类性能,既能提升对少数类的关注,又能保持多数类的分类准确度.Based on TrAdaboost,we propose an Unbalanced TrAdaboost(UBTA)algorithm which is a binary classification algorithm aiming to classify unbalanced data.UBTA calculates the weights of weak classifiers using the auprc(the Area Under the Precision-Recall Curve)of different classes and updates the weights of misclassified samples of different classes with different schemes.In combination with G-mean and BER,the AUC measure is more accurate when evaluating the performance of unbalanced classification since it is insensitive to changes in class distributions.The experiments indicate that the UBTA algorithm achieves better results for unbalanced data sets,strengthens the attention to the minority instances and maintains high classification accuracy for majority instances.

关 键 词：不平衡数据 分类 迁移学习 分类准确度 Precision-Recall曲线 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]