Abstract Unsupervised Domain Adaptation (UDA) aims to transfer domain knowledge from existing well-defifined tasks to new ones where labels are unavailable. In the real-world applications, as the domain (task) discrepancies are usually uncontrollable, it is signifificantly motivated to match the feature distributions even if the domain discrepancies are disparate. Additionally, as no label is available in the target domain, how to successfully adapt the classififier from the source to the target domain still remains an open question. In this paper, we propose the Re-weighted Adversarial Adaptation Network (RAAN) to reduce the feature distribution divergence and adapt the classififier when domain discrepancies are disparate. Specififically, to alleviate the need of common supports in matching the feature distribution, we choose to minimize optimal transport (OT) based EarthMover (EM) distance and reformulate it to a minimax objective function. Utilizing this, RAAN can be trained in an end-to-end and adversarial manner. To further adapt the classififier, we propose to match the label distribution and embed it into the adversarial training. Finally, after extensive evaluation of our method using UDA datasets of varying diffificulty, RAAN achieved the state-of-the-art results and outperformed other methods by a large margin when the domain shifts are disparate