Institutional Repository
| Cross-domain metric learning based on information theory | |
| Wang, Hao (1); Wang, Wei (2); Zhang, Chen (2); Xu, Fanjiang (2); Wang, Hao | |
| 2014 | |
| Conference Name | 28th AAAI Conference on Artificial Intelligence, AAAI 2014, 26th Innovative Applications of Artificial Intelligence Conference, IAAI 2014 and the 5th Symposium on Educational Advances in Artificial Intelligence, EAAI 2014 |
| Pages | 2099-2105 |
| Conference Date | July 27, 2014 - July 31, 2014 |
| Conference Place | Quebec City, QC, Canada |
| Indexed Type | EI |
| Publish Place | AI Access Foundation |
| ISBN | 9781577356790 |
| Department | (1) State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China; (2) Science and Technology on Integrated Information System Laboratory, Institute of Software, Chinese Academy of Sciences, Beijing, China; (3) Department of Automation, University of Science and Technology, China |
| English Abstract | Supervised metric learning plays a substantial role in statistical classification. Conventional metric learning algorithms have limited utility when the training data and testing data are drawn from related but different domains (i.e., source domain and target domain). Although this issue has got some progress in feature-based transfer learning, most of the work in this area suffers from non-trivial optimization and pays little attention to preserving the discriminating information. In this paper, we propose a novel metric learning algorithm to transfer knowledge from the source domain to the target domain in an information-theoretic setting, where a shared Mahalanobis distance across two domains is learnt by combining three goals together: 1) reducing the distribution difference between different domains; 2) preserving the geometry of target domain data; 3) aligning the geometry of source domain data with its label information. Based on this combination, the learnt Mahalanobis distance effectively transfers the discriminating power and propagates standard classifiers across these two domains. More importantly, our proposed method has closed-form solution and can be efficiently optimized. Experiments in two real-world applications demonstrate the effectiveness of our proposed method.; Supervised metric learning plays a substantial role in statistical classification. Conventional metric learning algorithms have limited utility when the training data and testing data are drawn from related but different domains (i.e., source domain and target domain). Although this issue has got some progress in feature-based transfer learning, most of the work in this area suffers from non-trivial optimization and pays little attention to preserving the discriminating information. In this paper, we propose a novel metric learning algorithm to transfer knowledge from the source domain to the target domain in an information-theoretic setting, where a shared Mahalanobis distance across two domains is learnt by combining three goals together: 1) reducing the distribution difference between different domains; 2) preserving the geometry of target domain data; 3) aligning the geometry of source domain data with its label information. Based on this combination, the learnt Mahalanobis distance effectively transfers the discriminating power and propagates standard classifiers across these two domains. More importantly, our proposed method has closed-form solution and can be efficiently optimized. Experiments in two real-world applications demonstrate the effectiveness of our proposed method. |
| Language | 英语 |
| Content Type | 会议论文 |
| URI | http://ir.iscas.ac.cn/handle/311060/16594 |
| Collection | 中国科学院软件研究所 |
| Corresponding Author | Wang, Hao |
| Recommended Citation GB/T 7714 | Wang, Hao ,Wang, Wei ,Zhang, Chen ,et al. Cross-domain metric learning based on information theory[C]. AI Access Foundation,2014:2099-2105. |
| Files in This Item: | There are no files associated with this item. | |||||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment