极端标签迁移下的基于类的子集选择迁移学习

迁移学习中的现有工作通常遵循两步流程——在大规模源域上进行预训练，然后在目标域的有限样本上进行微调。然而，尽管这种方法广受欢迎，但已被证明在存在分布迁移时会受到限制——具体而言，当输出空间发生 divergence 时。先前工作关注通过识别和分类仅在分布之间共享的输出类来提高模型性能。然而，这些方法本质上受限于忽略了共享类集之外的类， disregard of potentially relevant information for model transfer. This paper proposes a new process for few-shot transfer learning that selects and weighs classes from the source domain to optimize the transfer between domains. More concretely, we use Wasserstein distance to choose a set of source classes and their weights that minimize the distance between the source and target domain. To justify our proposed algorithm, we provide a generalization analysis of the performance of the learned classifier over the target domain and show that our method corresponds to a bound minimization algorithm. We empirically demonstrate the effectiveness of our approach (WaSS) by experimenting on several different datasets and presenting superior performance within various label shift settings, including the extreme case where the label spaces are disjoint. We empirically demonstrate the effectiveness of our approach (WaSS) by experimenting on several different datasets and presenting superior performance within various label shift settings, including the extreme case where the label spaces are disjoint.