期刊
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
卷 29, 期 6, 页码 1158-1171出版社
IEEE COMPUTER SOC
DOI: 10.1109/TKDE.2017.2669193
关键词
Transfer learning; metric learning; density ratio reweighting; Mahalanobis distance; learning framework
类别
资金
- NTU Singapore Nanyang Assistant Professorship (NAP) [M4081532.020]
- National Natural Science Foundation of China [71671069]
- Natural Science Foundation of Guangdong Province, China [2016A030313479]
- Mobile Research Foundation of Ministry of Education of China [MCM20160204]
- Fundamental Research Funds for the Central Universities
- Guangzhou Key Laboratory of Robotics and Intelligent Software [15180007]
Transfer learning has been proven to be effective for the problems where training data from a source domain and test data from a target domain are drawn from different distributions. To reduce the distribution divergence between the source domain and the target domain, many previous studies have been focused on designing and optimizing objective functions with the Euclidean distance to measure dissimilarity between instances. However, in some real-world applications, the Euclidean distance may be inappropriate to capture the intrinsic similarity or dissimilarity between instances. To deal with this issue, in this paper, we propose a metric transfer learning framework (MTLF) to encode metric learning in transfer learning. In MTLF, instance weights are learned and exploited to bridge the distributions of different domains, while Mahalanobis distance is learned simultaneously to maximize the intra-class distances and minimize the inter-class distances for the target domain. Unlike previous work where instance weights and Mahalanobis distance are trained in a pipelined framework that potentially leads to error propagation across different components, MTLF attempts to learn instance weights and a Mahalanobis distance in a parallel framework to make knowledge transfer across domains more effective. Furthermore, we develop general solutions to both classification and regression problems on top of MTLF, respectively. We conduct extensive experiments on several real-world datasets on object recognition, handwriting recognition, and WiFi location to verify the effectiveness of MTLF compared with a number of state-of-the-art methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据