Consider a domain-adaptive supervised learning setting, where a classifier learns from labeled data in a source domain and unlabeled data in a target domain to predict the corresponding target labels. If the classifier’s assumption on the relationship between domains (e.g. covariate shift, common subspace, etc.) is valid, then it will usually outperform a non-adaptive source classifier. If its assumption is invalid, it can perform substantially worse. Validating assumptions on domain relationships is not possible without target labels. We argue that, in order to make domain-adaptive classifiers more practical, it is necessary to focus on robustness; robust in the sense that an adaptive classifier will still perform at least as well as a non-adaptive classifier without having to rely on the validity of strong assumptions. With this objective in mind, we derive a conservative parameter estimation technique, which is transductive in the sense of Vapnik and Chervonenkis, and show for discriminant analysis that the new estimator is guaranteed to achieve a lower risk on the given target samples compared to the source classifier. Experiments on problems with geographical sampling bias indicate that our parameter estimator performs well.

考虑域自适应监督学习设置，其中分类器从源域中的标记数据和目标域中的未标记数据中学习，以预测相应的目标标签。如果分类器对域之间关系（例如协变量移位、公共子空间等）的假设是有效的，那么它通常会胜过非自适应源分类器。如果它的假设无效，它的性能可能会差很多. 如果没有目标标签，就不可能验证对域关系的假设。我们认为，为了使领域自适应分类器更实用，有必要关注鲁棒性；在某种意义上说，自适应分类器的性能至少与非自适应分类器一样好，而不必依赖强假设的有效性。考虑到这一目标，我们推导出了一种保守的参数估计技术，该技术在 Vapnik 和 Chervonenkis 的意义上是转导的，并为判别分析表明，与源相比，新的估计器保证在给定的目标样本上实现较低的风险分类器。关于地理抽样偏差问题的实验表明，我们的参数估计器表现良好。