arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.08161cs.LGstat.ML
收藏

条件域匹配和标签偏移的最优传输

Optimal Transport for Conditional Domain Matching and Label Shift

Criteo AI Lab(Criteo人工智能实验室);Ecole Polytechnique(巴黎综合理工学院);INSA de Rouen Normandie(鲁昂国立应用科学学院);Université Technologique de Compiègne(贡比涅技术大学);Université de Rouen Normandie(鲁昂诺曼底大学);Université de Bretagne Sud(南布列塔尼大学)

Alain Rakotomamonjy, Rémi Flamary, Gilles Gasso, Mokhtar Z. Alaya, Maxime Berar, Nicolas Courty

摘要:

我们解决了无监督的领域自适应的问题下设置的广义目标移位(联合类条件和标签偏移)。对于这个框架,我们从理论上表明,良好的推广,有必要学习一个潜在的表示,其中边缘和类条件分布跨域对齐。为此,我们提出了一个学习问题,最大限度地减少在源域的重要性加权损失和加权边缘之间的Wasserstein距离。对于一个适当的权重,我们提供了一个估计的目标标签的比例混合估计和最佳匹配的最佳运输。这种估计在温和的假设下具有正确性的理论保证。我们的实验结果表明,我们的方法在范围领域自适应问题,包括\emph{digits},\emph{VisDA}和\emph{Office}的平均表现优于竞争对手。本文的代码可在\url{https://github.com/arakotom/mars_domain_adaptation}上找到。

英文摘要:

We address the problem of unsupervised domain adaptation under the setting of generalized target shift (joint class-conditional and label shifts). For this framework, we theoretically show that, for good generalization, it is necessary to learn a latent representation in which both marginals and class-conditional distributions are aligned across domains. For this sake, we propose a learning problem that minimizes importance weighted loss in the source domain and a Wasserstein distance between weighted marginals. For a proper weighting, we provide an estimator of target label proportion by blending mixture estimation and optimal matching by optimal transport. This estimation comes with theoretical guarantees of correctness under mild assumptions. Our experimental results show that our method performs better on average than competitors across a range domain adaptation problems including \emph{digits},\emph{VisDA} and \emph{Office}. Code for this paper is available at \url{https://github.com/arakotom/mars_domain_adaptation}.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑