Semi-supervised domain adaptation via Fredholm integral based kernel methods
文献类型：期刊论文
| 作者 | Wang, Wei1; Wang, Hao2; Zhang, Zhaoxiang3 ; Zhang, Chen2; Gao, Yang1
|
| 刊名 | PATTERN RECOGNITION
 |
| 出版日期 | 2019 |
| 卷号 | 85页码:185-197 |
| 关键词 | Domain adaptation Semi-supervised learning Multiple kernel learning Hilbert space embedding of distributions |
| ISSN号 | 0031-3203 |
| DOI | 10.1016/j.patcog.2018.07.035 |
| 通讯作者 | Wang, Wei(wangwei2014@iscas.ac.cn) |
| 英文摘要 | Along with the emergence of domain adaptation in semi-supervised setting, dealing with the noisy and complex data in classifier adaptation underscores its growing importance. We believe a large amount of unlabeled data in target domain, which are always only used in distribution alignment, are more of a great source of information for this challenge. In this paper, we propose a novel Transfer Fredholm Multiple Kernel Learning (TFMKL) framework to suppress the noise for complex data distributions. Firstly, with exploring unlabeled target data, TFMKL learns a cross-domain predictive model by developing a Fredholm integral based kernel prediction framework which is proven to be effective in noise suppression. Secondly, TFMKL explicitly extends the applied range of unlabeled target samples into adaptive classifier building and distribution alignment. Thirdly, multiple kernels are explored to induce an optimal learning space. Correspondingly, TFMKL is distinguished with allowing for noise resiliency, facilitating knowledge transfer and analyzing complex data characteristics at the same time. Furthermore, an effective optimization procedure is presented based on the reduced gradient, guaranteeing rapid convergence. We emphasize the adaptability of TFMKL to different domain adaptation tasks due to its extension to different predictive models. In particular, two models based on square loss and hinge loss respectively are proposed within the TFMKL framework. Comprehensive empirical studies on benchmark data sets verify the effectiveness and the noise resiliency of our proposed methods. (C) 2018 Elsevier Ltd. All rights reserved. |
| WOS关键词 | REGULARIZATION ; REPRESENTATION ; CLASSIFIERS ; FRAMEWORK |
| 资助项目 | Natural Science Foundation of China[61502466] ; Natural Science Foundation of China[61773375] ; Natural Science Foundation of China[61672501] ; Natural Science Foundation of China[61602453] ; Beijing Municipal Natural Science Foundation[Z181100008918010] |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000447819300016 |
| 出版者 | ELSEVIER SCI LTD |
| 资助机构 | Natural Science Foundation of China ; Beijing Municipal Natural Science Foundation |
| 源URL | [http://ir.ia.ac.cn/handle/173211/22812]  |
| 专题 | 自动化研究所_智能感知与计算研究中心 |
| 通讯作者 | Wang, Wei |
| 作者单位 | 1.Chinese Acad Sci, Inst Software, Beijing, Peoples R China 2.360 Search Lab, Beijing 360, Peoples R China 3.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wang, Wei,Wang, Hao,Zhang, Zhaoxiang,et al. Semi-supervised domain adaptation via Fredholm integral based kernel methods[J]. PATTERN RECOGNITION,2019,85:185-197. |
| APA | Wang, Wei,Wang, Hao,Zhang, Zhaoxiang,Zhang, Chen,&Gao, Yang.(2019).Semi-supervised domain adaptation via Fredholm integral based kernel methods.PATTERN RECOGNITION,85,185-197. |
| MLA | Wang, Wei,et al."Semi-supervised domain adaptation via Fredholm integral based kernel methods".PATTERN RECOGNITION 85(2019):185-197. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。