Common-Decision-Vector Based Multiple Source Transfer Learning Classification and Its Fast Learning Method

ZHANG Jing-xiang; WANG Shi-tong

doi:10.3969/j.issn.0372-2112.2015.07.015

您当前的位置：

首页 >

文章列表页 >

Common-Decision-Vector Based Multiple Source Transfer Learning Classification and Its Fast Learning Method

更新时间：2025-07-16

- Common-Decision-Vector Based Multiple Source Transfer Learning Classification and Its Fast Learning Method
- Acta Electronica Sinica Vol. 43, Issue 7, Pages: 1349-1355(2015)
- 作者机构：
  
  1. 江南大学数字媒体学院,江苏,无锡,214122
  2. 江南大学理学院,江苏,无锡,214122
  3. 江南大学数字媒体学院,江苏,无锡,214122
  4. 江南大学理学院,江苏,无锡,214122
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.61202311, No.61272210);Doctoral Research Foundation of Jiangnan University (No.JUDCF13031);Graduate Research Innovation Program of univerities in Jiangsu Province (No.CXLX13-748)
- DOI：10.3969/j.issn.0372-2112.2015.07.015
  CLC： TP391.4
- Published：2015
- 稿件说明：
移动端阅览
ZHANG Jing-xiang, WANG Shi-tong. Common-Decision-Vector Based Multiple Source Transfer Learning Classification and Its Fast Learning Method[J]. Acta Electronica Sinica, 2015, 43(7): 1349-1355.
DOI：

ZHANG Jing-xiang, WANG Shi-tong. Common-Decision-Vector Based Multiple Source Transfer Learning Classification and Its Fast Learning Method[J]. Acta Electronica Sinica, 2015, 43(7): 1349-1355. DOI： 10.3969/j.issn.0372-2112.2015.07.015.

摘要

多源迁移学习提取了多个相似领域之间有用信息

提高了学习效率

但存在计算核矩阵的空间和时间复杂度较高的问题.提出了一种多源迁移学习方法

该方法基于结构风险最小框架理论

以共同决策方向矢量为基准

将多个相似领域的决策方向矢量嵌入到支持向量机的训练过程中

提高了目标领域分类器的分类性能.并结合核心向量机理论提出了共同决策方向矢量核心向量机

实现对大样本数据集的快速分类学习.模拟和真实数据集实验表明了所提算法的有效性.

Abstract

Multiple source transfer learning (MSTL) has been obtaining more and more applications especially from several related source domains to help the learning task on target domain.However

multiple source transfer learning algorithms often deal with the corresponding quadratic programming problems which may suffer a big computational burden caused by the kernel matrix computation.In this paper

a novel common-decision-vector based multiple source transfer classification learning (CDV-MSTL) is proposed which doesn't depend on the intrinsic structure of data.This algorithm is based on the structural risk minimization principle and the SVM like framework

so it has good adaptability and better accuracy.Based on the theory of CVM

CDV-MSTL is extended to its CVM based version which can realize fast training for large scale data.Extensive experiments on synthetic and real-world datasets demonstrate the significant improvement in classification performance obtained by the proposed algorithm over existing MSTL algorithm.

关键词

Keywords

references

Views

2138

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on Feature Selection Based on Hybrid Evolutionary Algorithm

Classification of Distributed GEP-BP Based on Grid Service

Classification of Tumor Gene Expression Data Based on Laplacian Spectra of Graphs

A Method of Ontology Mapping Based on Classifying Schema Structure

Effectiveness Analysis and Application in Data Streams of Cross Validation Noise-Tolerance Classification Algorithm

Related Author

GAO Hui-min

WANG Yun-he

BIAN Chuang

LI Xiang-tao

DENG Song

WANG Ru-chuan

WANG Nian

ZHUANG Zhen-hua

Related Institution

School of Artificial Intelligence， Jilin University

School of Artificial Intelligence， Hebei University of Technology

State Key Laboratory for Novel Software TechnologyNanjing UniversityNanjingJiangsu 210093China

School of Computer,Nanjing University Posts and Telecommunications Nanjing

State Key Laboratory for Novel Software Technology, Nanjing University

⁰