计算机科学与探索2025，Vol.19Issue(5)：1241-1251,11.DOI:10.3778/j.issn.1673-9418.2405070
动态自适应跨域均值逼近
Dynamic Adaptive Cross-Domain Mean Approximation
摘要
Abstract
Cross-domain mean approximation(CDMA)is an efficient measure of distributional differences between domains.It measures the sample distribution difference between domains by calculating the distance from a sample in one domain to the sample mean in another domain,which in turn can facilitate cross-domain migration of knowledge.How-ever,in practical applications,the marginal and conditional distributions of data are unbalanced,and CDMA pursues equally measuring the difference between the marginal and conditional distributions without considering the difference be-tween the two,which leads to its inefficiency in transfer learning.For this reason,this paper firstly improves CDMA by intro-ducing an adaptation factor and designing dynamic CDMA to evaluate the edge distribution error and conditional distribu-tion error between the source and target domains.Secondly,on the basis of dynamic CDMA,a dynamic adaptive cross-domain mean approximation(DA-CDMA)feature extraction algorithm is proposed to extract features that are invariant between domains in order to realize cross-domain migration of knowledge.In addition,in order to reduce the shift of mean value caused by individual bad samples far away from the mean center during the feature extraction process,a mean update mechanism is proposed to update the mean value within the class to increase the stability and accuracy of migration.Finally,clas-sification experiments are conducted on publicly available migration learning datasets to verify the effectiveness of the method.关键词
分布差异/跨域均值逼近/动态自适应/分布差异度量/分类/均值更新Key words
distribution difference/cross-domain mean approximation/dynamic adaptation/distribution difference mea-surement/classification/mean updating分类
信息技术与安全科学引用本文复制引用
李慧敏,马建伟,臧绍飞,宋彦兵..动态自适应跨域均值逼近[J].计算机科学与探索,2025,19(5):1241-1251,11.基金项目
河南省高等学校重点科研项目(22A120005) （22A120005）
河南省重点研发与推广专项(科技攻关)项目(222102210095). This work was supported by the Key Research Project of Higher Education Institutions in Henan Province(22A120005),and the Key Research,Development and Promotion Special(Scientific and Technological Research)Project in Henan Province(222102210095). （科技攻关）
