Joint Information Preservation for Heterogeneous Domain Adaptation
Heterogeneous domain adaptation (HDA) aims to assist the modeling tasks of the target domain lied in different spaces with knowledge of the source domain. A core issue of HDA is how to preserve the information of the original data during domain adaptation and eliminate the information loss caused by...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press
2020-07-01
|
| Series: | Jisuanji kexue yu tansuo |
| Subjects: | |
| Online Access: | http://fcst.ceaj.org/CN/abstract/abstract2267.shtml |
| _version_ | 1819081282370404352 |
|---|---|
| author | XU Peng, DENG Zhaohong, WANG Jun, WANG Shitong |
| author_facet | XU Peng, DENG Zhaohong, WANG Jun, WANG Shitong |
| author_sort | XU Peng, DENG Zhaohong, WANG Jun, WANG Shitong |
| collection | DOAJ |
| description | Heterogeneous domain adaptation (HDA) aims to assist the modeling tasks of the target domain lied in different spaces with knowledge of the source domain. A core issue of HDA is how to preserve the information of the original data during domain adaptation and eliminate the information loss caused by feature transformation. This paper proposes a joint information preservation (JIP) method to deal with the problem. The method preserves the information of the original data from two aspects. On the one hand, large number of paired samples often exist between the two domains of the HDA and the proposed method preserves the paired information by maximizing the correlation of the paired samples. On the other hand, the proposed method improves the strategy of preserving the structural information of the original data, where the local and global structural information are preserved simultaneously. Finally, the JIP is integrated with distribution matching to achieve HDA tasks. Experimental results show the superiority of the proposed method over the state-of-the-art HDA algorithms. |
| first_indexed | 2024-12-21T19:58:18Z |
| format | Article |
| id | doaj.art-82147575a9b7426997f64b910cc68694 |
| institution | Directory Open Access Journal |
| issn | 1673-9418 |
| language | zho |
| last_indexed | 2024-12-21T19:58:18Z |
| publishDate | 2020-07-01 |
| publisher | Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press |
| record_format | Article |
| series | Jisuanji kexue yu tansuo |
| spelling | doaj.art-82147575a9b7426997f64b910cc686942022-12-21T18:52:02ZzhoJournal of Computer Engineering and Applications Beijing Co., Ltd., Science PressJisuanji kexue yu tansuo1673-94182020-07-011471183119310.3778/j.issn.1673-9418.1905085Joint Information Preservation for Heterogeneous Domain AdaptationXU Peng, DENG Zhaohong, WANG Jun, WANG Shitong0School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, Jiangsu 214122, ChinaHeterogeneous domain adaptation (HDA) aims to assist the modeling tasks of the target domain lied in different spaces with knowledge of the source domain. A core issue of HDA is how to preserve the information of the original data during domain adaptation and eliminate the information loss caused by feature transformation. This paper proposes a joint information preservation (JIP) method to deal with the problem. The method preserves the information of the original data from two aspects. On the one hand, large number of paired samples often exist between the two domains of the HDA and the proposed method preserves the paired information by maximizing the correlation of the paired samples. On the other hand, the proposed method improves the strategy of preserving the structural information of the original data, where the local and global structural information are preserved simultaneously. Finally, the JIP is integrated with distribution matching to achieve HDA tasks. Experimental results show the superiority of the proposed method over the state-of-the-art HDA algorithms.http://fcst.ceaj.org/CN/abstract/abstract2267.shtmlheterogeneous domain adaptation (hda)information losspaired information |
| spellingShingle | XU Peng, DENG Zhaohong, WANG Jun, WANG Shitong Joint Information Preservation for Heterogeneous Domain Adaptation Jisuanji kexue yu tansuo heterogeneous domain adaptation (hda) information loss paired information |
| title | Joint Information Preservation for Heterogeneous Domain Adaptation |
| title_full | Joint Information Preservation for Heterogeneous Domain Adaptation |
| title_fullStr | Joint Information Preservation for Heterogeneous Domain Adaptation |
| title_full_unstemmed | Joint Information Preservation for Heterogeneous Domain Adaptation |
| title_short | Joint Information Preservation for Heterogeneous Domain Adaptation |
| title_sort | joint information preservation for heterogeneous domain adaptation |
| topic | heterogeneous domain adaptation (hda) information loss paired information |
| url | http://fcst.ceaj.org/CN/abstract/abstract2267.shtml |
| work_keys_str_mv | AT xupengdengzhaohongwangjunwangshitong jointinformationpreservationforheterogeneousdomainadaptation |