arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2202.05797cs.LG
收藏

分布鲁棒数据连接

Distributionally Robust Data Join

Google(谷歌);Stanford University(斯坦福大学);Google Research(谷歌研究院);University of Washington(华盛顿大学)

Pranjal Awasthi, Christopher Jung, Jamie Morgenstern

AI总结:

针对带标签与含辅助特征的无标签数据集分布不同但均接近测试分布的场景,提出一种推广的分布鲁棒优化方法,构建在两类Wasserstein距离约束下最小化最大损失的预测器。

摘要:

假设我们有两个数据集:一个带标签数据集和一个无标签数据集,后者还包含第一个数据集所没有的额外辅助特征。最具原则性的方式是如何联合使用这些数据集来构建预测器?答案应取决于这两个数据集在其共有特征集上是由相同还是不同的分布生成,以及测试分布与这两种分布的相似程度。在许多应用中,两个数据集很可能遵循不同的分布,但两者都可能接近测试分布。我们提出了构建预测器的问题,该预测器在所有关于原始特征、辅助特征和二元标签的概率分布上最小化最大损失,这些分布与带标签数据集的经验分布的Wasserstein距离为$r_1$,与无标签数据集的经验分布的Wasserstein距离为$r_2$。这可以被视为分布鲁棒优化(DRO)的一种推广,它允许使用两个数据源,其中一个是无标签的,且可能包含辅助特征。

英文摘要:

Suppose we are given two datasets: a labeled dataset and unlabeled dataset which also has additional auxiliary features not present in the first dataset. What is the most principled way to use these datasets together to construct a predictor? The answer should depend upon whether these datasets are generated by the same or different distributions over their mutual feature sets, and how similar the test distribution will be to either of those distributions. In many applications, the two datasets will likely follow different distributions, but both may be close to the test distribution. We introduce the problem of building a predictor which minimizes the maximum loss over all probability distributions over the original features, auxiliary features, and binary labels, whose Wasserstein distance is $r_1$ away from the empirical distribution over the labeled dataset and $r_2$ away from that of the unlabeled dataset. This can be thought of as a generalization of distributionally robust optimization (DRO), which allows for two data sources, one of which is unlabeled and may contain auxiliary features.

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。

↑