首页|Maximizing conditional independence for unsupervised domain adaptation

Maximizing conditional independence for unsupervised domain adaptation

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
Unsupervised domain adaptation(UDA)studies how to transfer a learner from a labeled source domain to an unlabeled target domain with different distributions.Existing methods mainly focus on match-ing marginal distributions of the source and target domains,which probably leads to a misalignment of sam-ples from the same class but different domains.In this paper,we tackle this misalignment issue by achieving the class-conditioned transferring from a new perspective.Specifically,we propose a method named maximiz-ing conditional independence(MCI)for UDA,which maximizes the conditional independence of feature and domain given class in the reproducing kernel Hilbert spaces.The optimization of conditional independence can be viewed as a surrogate for minimizing class-wise mutual information between feature and domain.An interpretable empirical estimation of the conditional dependence measure is deduced and connected with the unconditional case.Besides,we provide an upper bound on the target error by taking the class-conditional distribution into account,which provides a new theoretical insight for class-conditioned transferring.Ex-tensive experiments on six benchmark datasets and various ablation studies validate the effectiveness of the proposed model in dealing with UDA.

conditional independencekernel methoddomain adaptationclass-conditioned transferring

Yiming ZHAI、Chuanxian REN、Youwei LUO、Daoqing DAI

展开 >

School of Mathematics,Sun Yat-Sen University,Guangzhou 510275,China

National Natural Science Foundation of ChinaNational Natural Science Foundation of ChinaGuangdong Basic and Applied Basic Research FoundationOpen Research Projects of Zhejiang LabGuangdong Province Key Laboratory of Computational Science at the Sun Yat-Sen UniversityKey Laboratory of Machine Intelligence and Advanced Computing,Ministry of Education

61976229623762912023B15150200042021KHOABO82020B1212060032

2024

10.1007/s11432-022-3851-1

中国科学:信息科学(英文版)
中国科学院

中国科学:信息科学(英文版)

CSTPCDEI
影响因子：0.715
ISSN：1674-733X
年,卷(期)：2024.67(5)
  • 51