Homogeneous Domain Adaptation Transfer Learning Based on Score Sample Selection
DONG Yingying
DENG Wanyu
LIU Guangda
Abstract：Feature transformation focuses on the common features among learning domains. However,it ignores the negative effects of some samples on the results,which makes the accuracy of algorithm affected. In order to solve this problem,this paper proposes an Homogeneous domain adaptation learning algorithm based on score sample selection. The algorithm extracts the label from the source data which is similar to the target-domain sample distribution and relates the knowledge transformation from the source domain to the target domain. At the same time,based on the empirical risk minimum framework,the domain adaptation score of the source domain and the target domain samples are calculated. Then,the subset of the source domain is selected and solved iteratively. It automatically selects marker samples on the shared feature subspace and uses these samples to construct the auxiliary domain adaptation task between source domain and target domain. Experimental results verify the effectiveness of the algo?rithm.
Keywords：transfer learninghomogeneous domain adaptationlandmark sample selectionscore
Publication Date：2019-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 2989-2992,3153 )