期刊文献+

TL-SVM:一种迁移学习算法 被引量:14

TL-SVM: A transfer learning algorithm
原文传递
导出
摘要 迁移学习旨在利用大量已标签源域数据解决相关但不相同的目标域问题.当与某领域相关的新领域出现时,若重新标注新领域,则样本代价昂贵,丢弃所有旧领域数据又十分浪费.对此,基于SVM算法提出一种新颖的迁移学习算法—–TL-SVM,通过使用目标域少量已标签数据和大量相关领域的旧数据来为目标域构建一个高质量的分类模型,该方法既继承了基于经验风险最小化最大间隔SVM的优点,又弥补了传统SVM不能进行知识迁移的缺陷.实验结果验证了该算法的有效性. Transfer learning(TL) aims to solve related but different target domain problems by using plenty of labeled source domain data. When the task from one new domain comes, new domain samples are relabeled costly, and it would be a waste to discard all the old domain data. Therefore, an algorithm called TL-SVM based on the SVM algorithm is proposed, which uses a small amount of target domain tag data and a large number of source domain old data to build a high-quality classification model. The method inherits the advantages of the maximum interval SVM based on empirical risk minimization and makes up for the defects that traditional SVM can not migrate knowledge. Experimental results show the effectiveness of the proposed algorithm.
出处 《控制与决策》 EI CSCD 北大核心 2014年第1期141-146,共6页 Control and Decision
基金 国家自然科学基金项目(61272210 61170122) 江苏省研究生创新工程项目(CXZZ12-0759)
关键词 迁移学习 分类 支持向量机 transfer learning classification support vector machine
  • 相关文献

参考文献4

二级参考文献14

  • 1Pan S J, Yang Q. A survey on transfer learning [ J]. IEEE Trans- actions on Knowledge and Data Engineering, 2010,22 ( 10 ) : 1345 - 1359.
  • 2Dai W, Yang Q, Xue G, et al. Boosting for uansferleamig[ C]. In Proceedings of the 24th International Conference on Machine Learn- ing, 2007:193-200.
  • 3Zhu X. Semi-supervised learning literature survey [R]. Madison: Department of Computer Sciences, University of Wisconsin,2005.
  • 4Bennett K P,Demifiz A, Maclin R. Exploiting unlabeled data in ensemble methods [ C]. In Proceedings of the 8th Knowledge Dis- cover), and Data Mining, 2002:289-296.
  • 5Shi Y, Lan Z, Liu W, et al. Extending semi-supervised learning methods for inductive transfer learning [ C]. In Proceedings of the 9th International Conference on Data M/ning, 2009:483-492.
  • 6Xie S, Fan W, Peng J, et al. Latent space domain transfer between high dimensional overlapping distributions CC]. In Proceedings of the 18th International Conference on World Wide Web, 2009:91- 100.
  • 7Pan S J, Ni X,-Sun J, et al. Cross-domain sentiment classification via spectral feature alignment [ C ]. In Proceedings of the 19th In- ternational Conference on World Wide Web, 2010:751-760.
  • 8Freund Y, Schapire R E. A decision-theoretic generalization of on- line learning and an application to boosting [J]. Journal of Com- puter and System Sciences, 1997,55 : 119-139.
  • 9Mason L, Baxter J, Bartlett P, et al. Functional gradient tech- niques for combining hypotheses [ A]. In: SchoIkopf B, Smola A, Bartlett P, et 81 ed. Advances in Large Margin Classifiers [ C]. Cambridge: MIT Press, 2000:221-246.
  • 10Joachims T. Transductive inference for text classification using support vector machines [C]. In Proceedings of the 1601 Interna- tional Conference on Mach/ne/.ezra/rig, 1999:200-209.

共引文献17

同被引文献75

  • 1Shao L, Zhu F, Li X. Transfer learning for visual categorization: A survey[J]. IEEE Transactions on Neural Networks and Learning Systems, 2014, 26(5): 1019-1034.
  • 2Jia C, Kong Y, Ding Z, et al. Latent tensor transfer learning for RGB-D action recognition[C]//Proceedings of the ACM International Conference on Multimedia. New York, NJ, USA: ACM, 2014: 87-96.
  • 3Perlich C, Dalessandro B, Raeder T, et al. Machine learning for targeted display advertising: Transfer learning in action[J]. Machine Learning, 2014, 95(1): 103-127.
  • 4Zhuang F, Luo P, Xiong H, et al. Exploiting associations between word clusters and document classes for cross-domain text categorization[J]. Statistical Analysis and Data Mining: The ASA Data Science Journal, 2011, 4(1): 100-114.
  • 5Dai W, Xue G R, Yang Q, et al. Co-clustering based classification for out-of-domain documents[C]//Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining. New York, NJ, USA: ACM, 2007: 210-219.
  • 6Zhou J T, Pan S J, Tsang I W, et al. Hybrid heterogeneous transfer learning through deep learning[C]//Twenty-Eighth AAAI Conference on Artificial Intelligence. Menlo Park, USA: AAAI, 2014: 2213-2219.
  • 7Yang P, Gao W. Multi-view discriminant transfer learning[C]//Proceedings of the Twenty-Third international joint conference on Artificial Intelligence. Menlo Park, USA: AAAI, 2013: 1848-1854.
  • 8Zhang M L, Zhou Z H. A review on multi-label learning algorithms[J]. IEEE Transactions on Knowledge and Data Engineering, 2014, 26(8): 1819-1837.
  • 9Mei S. Predicting plant protein subcellular multi-localization by Chou's PseAAC formulation based multi-label homolog knowledge transfer learning[J]. Journal of Theoretical Biology, 2012, 310: 80-87.
  • 10Tawiah C, Sheng V. Empirical comparison of multi-label classification algorithms[C]//Twenty-Seventh AAAI Conference on Artificial Intelligence. Menlo Park, USA: AAAI, 2013: 1645-1646.

引证文献14

二级引证文献53

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部