Zhangjie Cao, Mingsheng Long, Jianmin Wang, Michael I. Jordan
TL;DR该研究论文介绍了一种名为Selective Adversarial Network (SAN)的选择性对抗网络，用于解决部分转移学习（partial transfer learning）问题，从而实现大数据时代的分类和特征转移学习优化。实验结果显示，我们的模型优于多个基准数据集上的现有最先进结果。
Abstract
adversarial learning has been successfully embedded into deep networks to learn transferable features, which reduce distribution discrepancy between the source and target domains. Existing domain adversarial networks assume fully shared label space across domains. In the presence of