The number of available online services increases sharply with the development of the Internet. These services typically belong to varying service domains. To address the data-sparse issue, cross-domain recommendation techniques are proposed to transfer the information in relevant service domains to improve the recommendation effects. In this paper, we presented a novel end-to-end cross-domain service recommendation learning framework, named EATN, short for End-to-end Attention Transfer Network, which is different from most existing cross-domain step-by-step learning frameworks. To realize this end-to-end framework, we design a workflow to achieve user preferences cross-domain matching procedure. We capture fine-grained and multi-faceted user preferences by using multiple Multi-Layer Perceptron layers. To reasonably integrate multi-faceted transfer preferences, we design a service-level attention module, which learns weight based on the relevance to services. Finally, it can improve the recommendation effect of cold-start users in the target domain. Extensive experiments on the real-world Amazon dataset show the significant improvement of our proposed EATN framework.