Sign Prediction on Unlabeled Social Networks Using Branch and Bound Optimized Transfer Learning
Sign prediction problem aims to predict the signs of links for signed networks. Currently it has been widely used in a variety of applications. Due to the insufficiency of labeled data, transfer learning has been adopted to leverage the auxiliary data to improve the prediction of signs in target dom...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2019/4906903 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832568332521308160 |
|---|---|
| author | Weiwei Yuan Jiali Pang Donghai Guan Yuan Tian Abdullah Al-Dhelaan Mohammed Al-Dhelaan |
| author_facet | Weiwei Yuan Jiali Pang Donghai Guan Yuan Tian Abdullah Al-Dhelaan Mohammed Al-Dhelaan |
| author_sort | Weiwei Yuan |
| collection | DOAJ |
| description | Sign prediction problem aims to predict the signs of links for signed networks. Currently it has been widely used in a variety of applications. Due to the insufficiency of labeled data, transfer learning has been adopted to leverage the auxiliary data to improve the prediction of signs in target domain. Existing works suffer from two limitations. First, they cannot work if there is no target label available. Second, their generalization performance is not guaranteed due to that fact that the solution of their objective functions is not global optimal solution. To solve these problems, we propose a novel sign prediction on unlabeled social networks using branch and bound optimized transfer learning (SP_BBTL) sign prediction model. The main idea of SP_BBTL is to use target feature vectors to reconstruct source domain feature vectors based on relationship projection, which is a complicated optimal problem and is solved by proposed optimization based on branch and bound that can obtain global optimal solution. With this design, the target domain label information is not required for classifier. Finally, the experimental results on the large scale social signed networks validate the superiority of the proposed model. |
| format | Article |
| id | doaj-art-04436933a1b646829befcaca85e8a086 |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2019-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-04436933a1b646829befcaca85e8a0862025-02-03T00:59:12ZengWileyComplexity1076-27871099-05262019-01-01201910.1155/2019/49069034906903Sign Prediction on Unlabeled Social Networks Using Branch and Bound Optimized Transfer LearningWeiwei Yuan0Jiali Pang1Donghai Guan2Yuan Tian3Abdullah Al-Dhelaan4Mohammed Al-Dhelaan5College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, ChinaCollege of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, ChinaCollege of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, ChinaSchool of Computer Engineering, Nanjing Institute of Technology, Nanjing 211816, ChinaDept. of Computer Science, King Saud University, Riyadh, Saudi ArabiaDept. of Computer Science, King Saud University, Riyadh, Saudi ArabiaSign prediction problem aims to predict the signs of links for signed networks. Currently it has been widely used in a variety of applications. Due to the insufficiency of labeled data, transfer learning has been adopted to leverage the auxiliary data to improve the prediction of signs in target domain. Existing works suffer from two limitations. First, they cannot work if there is no target label available. Second, their generalization performance is not guaranteed due to that fact that the solution of their objective functions is not global optimal solution. To solve these problems, we propose a novel sign prediction on unlabeled social networks using branch and bound optimized transfer learning (SP_BBTL) sign prediction model. The main idea of SP_BBTL is to use target feature vectors to reconstruct source domain feature vectors based on relationship projection, which is a complicated optimal problem and is solved by proposed optimization based on branch and bound that can obtain global optimal solution. With this design, the target domain label information is not required for classifier. Finally, the experimental results on the large scale social signed networks validate the superiority of the proposed model.http://dx.doi.org/10.1155/2019/4906903 |
| spellingShingle | Weiwei Yuan Jiali Pang Donghai Guan Yuan Tian Abdullah Al-Dhelaan Mohammed Al-Dhelaan Sign Prediction on Unlabeled Social Networks Using Branch and Bound Optimized Transfer Learning Complexity |
| title | Sign Prediction on Unlabeled Social Networks Using Branch and Bound Optimized Transfer Learning |
| title_full | Sign Prediction on Unlabeled Social Networks Using Branch and Bound Optimized Transfer Learning |
| title_fullStr | Sign Prediction on Unlabeled Social Networks Using Branch and Bound Optimized Transfer Learning |
| title_full_unstemmed | Sign Prediction on Unlabeled Social Networks Using Branch and Bound Optimized Transfer Learning |
| title_short | Sign Prediction on Unlabeled Social Networks Using Branch and Bound Optimized Transfer Learning |
| title_sort | sign prediction on unlabeled social networks using branch and bound optimized transfer learning |
| url | http://dx.doi.org/10.1155/2019/4906903 |
| work_keys_str_mv | AT weiweiyuan signpredictiononunlabeledsocialnetworksusingbranchandboundoptimizedtransferlearning AT jialipang signpredictiononunlabeledsocialnetworksusingbranchandboundoptimizedtransferlearning AT donghaiguan signpredictiononunlabeledsocialnetworksusingbranchandboundoptimizedtransferlearning AT yuantian signpredictiononunlabeledsocialnetworksusingbranchandboundoptimizedtransferlearning AT abdullahaldhelaan signpredictiononunlabeledsocialnetworksusingbranchandboundoptimizedtransferlearning AT mohammedaldhelaan signpredictiononunlabeledsocialnetworksusingbranchandboundoptimizedtransferlearning |