Heterogeneous transfer learning based on translation invariant kernels
Author(s): GUAN Zengda, CHENG Li, ZHU Tingshao, School of Computer and Control, University of Chinese Academy of Sciences, Bioinformatics Institute, A*STAR, School of Computing, National University of Singapore, Institute of Psychology, Chinese Academy of Sciences
Pages: 121-126
Year: 2015 Issue: 1
Journal: Journal of the Graduate School of the Chinese Academy of Sciences
Keyword: heterogeneous transfer learning; translation invariant kernel; RKHS;
Abstract: 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%.
Pages: 121-126
Year: 2015 Issue: 1
Journal: Journal of the Graduate School of the Chinese Academy of Sciences
Keyword: heterogeneous transfer learning; translation invariant kernel; RKHS;
Abstract: 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%.
Related Articles