核典型关联性分析相关特征提取与核逻辑斯蒂回归域自适应学习  

Domain Adaptation Learning with Kernel Logistic Regression and Kernel Canonical Correlation Analysis

作　　者：刘建伟[1] 孙正康 刘泽宇[2] 罗雄麟[1] 

机构地区：[1]中国石油大学(北京)自动化系,北京102249 [2]中国科学院软件研究所基础软件国家工程研究中心,北京100190

出　　处：《电子学报》2016年第12期2908-2915,共8页Acta Electronica Sinica

基　　金：国家重点基础研究发展规划(973计划)项目(No.2012CB720500)

摘　　要：本文提出了一种利用核典型关联性分析提取源域目标域最大相关特征,使用核逻辑斯蒂回归模型进行域自适应学习的算法,该算法称为KCCA-DAML(Kernel Canonical Correlation Analysis for Domain Adaptation Learning).该算法基于特征集关联性分析,有效的减小源域和目标域的概率分布差异性,利用提取的最大相关特征通过核逻辑斯蒂回归模型实现源域到目标域的跨域学习.实验比较源域数据上核逻辑斯蒂学习模型、目标域上核逻辑斯蒂学习模型、源域和目标域上核逻辑斯蒂学习模型和KCCA-DAML模型,结果显示KCCA-DAML在真实数据集上成功的实现了跨域学习.The domain adaptive learning algorithm using kernel logistic regression model is proposed. The proposed ap- proach use kernel canonical correlation analysis to extract the maximum relevant features of the source and target domain. We dub it as KCCA-DAML（Kernel Canonical Correlation Analysis for Domain Adaptation Learning, KCCA-DAML）. Our algorithm is based on canonical correlation analysis, which simultaneously minimizes the incompatibility among source features ,target features and instance labels,extract maximum relevant features from source features ,target features and instance labels, and use kernel lo- gistic regression domain adaptation learning. In experimental comparison of the kernel logistic model and KCCA-DAML model on source domain data,the target domain data,source and the target domain data,we demonstrate the power of our techniques with the following real-world data sets：Reuters 20 Newsgroups ,MNIST handwritten-digits and UCI Dermatology.

关 键 词：域自适应 概率分布差异 相关分析 核逻辑斯蒂回归 正则化模型 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]