Asymmetric alignment joint consistent regularization for multi-source domain adaptation

Most existing methods of domain adaptation are proposed for single-source settings, where the source data come from a single domain. However, in practice, the available data generally come from multiple domains with different distributions. In this paper, we propose asymmetric alignment joint consistent regularization (AACR) for multi-source domain adaptation. As for asymmetric alignment, we propose to learn asymmetric projections, explicitly treating each domain differently to avoid the loss of shared information. Data from different domains are encoded into a common subspace by these asymmetric projections, where the encoded features are further aligned to promote knowledge transfer. Further, we propose consistent regularization to better learn shared information and filter out domain-specific information. We formulate the two parts into a unified framework, and derive its global optimal solution. Comprehensive experiments are conducted to evaluate AACR, and the results verify the effectiveness and robustness of our method.