Unsupervised Domain Adaptation Through Transferring both the Source-Knowledge and Target-Relatedness Simultaneously

Unsupervised domain adaptation (UDA) is an emerging research topic in the field of machine learning and pattern recognition, which aims to help the learning of unlabeled target domain by transferring knowledge from the source domain. To perform UDA, a variety of methods have been proposed, most of which concentrate on the scenario of single source and single target domain (1S1T). However, in real applications, usually single source domain with multiple target domains are involved (1SmT), which cannot be handled directly by those 1S1T models. Unfortunately, although a few related works on 1SmT UDA have been proposed, nearly none of them model the source domain knowledge and leverage the target-relatedness jointly. To overcome these shortcomings, we herein propose a more general 1SmT UDA model through transferring both the Source-Knowledge and Target-Relatedness, UDA-SKTR for short. In this way, not only the supervision knowledge from the source domain, but also the potential relatedness among the target domains are simultaneously modeled for exploitation in the process of 1SmT UDA. In addition, we construct an alternating optimization algorithm to solve the variables of the proposed model with convergence guarantee. Finally, through extensive experiments on both benchmark and real datasets, we validate the effectiveness and superiority of the proposed method.

Domain Adaptation Through Transferring both the Source-Knowledge and Target-Relatedness Simultaneously

Domain adaptation (DA) is an emerging research topic in the field of machine learning and pattern recognition, which aims to assist the learning of target domains by transferring model knowledge from the source domains. To perform DA, a variety of methods have been proposed, most of which concentrate on the scenario of single source and single target domain (1S1T). However, in real applications, usually multiple domains, especially target domains, are involved, which cannot be handled directly by those 1S1T models. Although related works on multi-target domains have been proposed, they are quite rare, and more unfortunately, nearly none of them model the source domain knowledge and leverage the target-relatedness jointly. To overcome these shortcomings, in this paper we propose a kind of DA model through TrAnsferring both the source-KnowlEdge and TargEt-Relatedness, DATAKETER for short. In this way, not only the supervision knowledge from the source domain, but also the potential relatedness among the target domains are simultaneously modeled for exploitation in the process of 1SmT DA. In addition, we construct an alternating optimization algorithm to solve the variables of the proposed model with convergence guarantee. Finally, through extensive experiments on both benchmark and real datasets, we validate the effectiveness and superiority of the proposed method.