|
基于平移不变核的异构迁移学习
Heterogeneous transfer learning based on translation invariant kernels
查看参考文献11篇
文摘
|
提出一种新的异构迁移学习方法. 利用与目标数据集相关的异构特征数据集. 通过把目标集和异构集的数据使用平移不变核(欧式距离核和径向基函数核),映射到一个新的再生核希尔伯特空间上. 在新空间中2个数据集的特征相同,特征维度相等,分布接近,且保持数据的拓扑性质不变. 实验证明,该方法特别是基于欧式距离核的方法取得了较好的效果,在目标训练集的标注数据较少时,有大于5%甚至超过10%的精度提高. |
其他语种文摘
|
We propose a new heterogeneous transfer learning method, which uses related heterogeneous feature dataset.We use translation invariant kernels (Euclidean kernels and RBF kernels) to map the target dataset and the related dataset to a new reproducing kernel Hilbert space, in which the two datasets have equal feature dimensions and similar distributions and reserve their topological property.The experimental results show that our method works well and the method based on the Euclidean kernel improves accuracy by more than 5% ~ 10%. |
来源
|
中国科学院大学学报
,2015,32(1):121-126 【核心库】
|
关键词
|
异构迁移学习
;
平移不变核
;
RKHS
|
地址
|
1.
中国科学院大学计算机与控制学院, 北京, 101408
2.
新加坡科技研究局生物信息研究所, 新加坡, 138671
3.
中国科学院心理研究所, 北京, 100101
|
语种
|
中文 |
文献类型
|
研究性论文 |
ISSN
|
2095-6134 |
学科
|
自动化技术、计算机技术 |
基金
|
国家973计划
;
中国科学院重点项目
;
中国科学院战略性先导科技专项
|
文献收藏号
|
CSCD:5340392
|
参考文献 共
11
共1页
|
1.
Pan S J. A survey on transfer learning.
IEEE Transactions on Knowledge and Data Engineering,2010,22(10):1345-1359
|
被引
701
次
|
|
|
|
2.
Yang Q. Heterogeneous transfer learning for image clustering via the social web.
Proceedings of the 47th Annual Meeting of the ACL and the 4th IJCNLP of the AFNLP,2009:1-9
|
被引
1
次
|
|
|
|
3.
Zhu Y. Heterogeneous transfer learning for image classification.
Proceedings of the 25th AAAI Conference on Artificial Intelligence,2011:1304-1309
|
被引
2
次
|
|
|
|
4.
Dai W Y. Translated learning: transfer learning across different feature spaces.
Proc 21st Ann Conf Neural Information Processing Systems,2008
|
被引
1
次
|
|
|
|
5.
Wang C. Heterogeneous domain adaptation using manifold alignment.
Proc 22nd International Joint Conference on Artificial Intelligence,2011:1541-1546
|
被引
1
次
|
|
|
|
6.
Duan L. Learning with augmented features for heterogeneous domain adaptation.
Proceedings of the 29th International Conference on Machine Learning,2012
|
被引
1
次
|
|
|
|
7.
Kulis B. What you saw is not what you get: domain adaptation using asymmetric kernel transforms.
Computer Vision and Pattern Recognition,2011:1785-1792
|
被引
1
次
|
|
|
|
8.
Guan Z D. Heterogeneous domain adaptation using linear kernel.
ICPCA-SWS,2013
|
被引
1
次
|
|
|
|
9.
Gu Q Q. Learning a kernel for multi-task clustering.
Proceedings of the 25th AAAI Conference on Artificial Intelligence,2011
|
被引
1
次
|
|
|
|
10.
Pan S J. Domain adaptation via transfer component analysis.
IEEE Transactions on Neural Networks,2011,22(2):199-210
|
被引
199
次
|
|
|
|
11.
Gretton A. A kernel method for the two-sample-problem.
Proceedings of the 2006 Conference Advances in Neural Information Processing Systems 19. 20,2006:513-520
|
被引
1
次
|
|
|
|
|
|