Maximizing conditional independence for unsupervised domain adaptation

Yiming ZHAI ¹Chuanxian REN ¹Youwei LUO ¹Daoqing DAI¹

扫码查看

作者信息

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

Abstract

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.

Key words

conditional independence/kernel method/domain adaptation/class-conditioned transferring

引用本文复制引用

基金项目

National Natural Science Foundation of China(61976229)

National Natural Science Foundation of China(62376291)

Guangdong Basic and Applied Basic Research Foundation(2023B1515020004)

Open Research Projects of Zhejiang Lab(2021KHOABO8)

Guangdong Province Key Laboratory of Computational Science at the Sun Yat-Sen University(2020B1212060032)

Key Laboratory of Machine Intelligence and Advanced Computing,Ministry of Education()

出版年

2024

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

参考文献量51

段落导航