arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1806.11345cs.LGstat.ML
收藏

测量竞赛中使用的合成数据的质量

Measuring the quality of Synthetic data for use in competitions

University of Oxford(牛津大学);University of California, Los Angeles(加利福尼亚大学洛杉矶分校)

James Jordon, Jinsung Yoon, Mihaela van der Schaar

摘要:

机器学习有可能帮助许多社区使用越来越多的大型数据集。不幸的是,这种潜力的大部分尚未实现,因为它需要以损害隐私的方式共享数据。为了克服这一障碍,已经提出了几种方法,这些方法生成合成数据,同时保留真实数据的隐私。在本文中,我们考虑了合成数据应该具有的一个关键特性,以便对机器学习研究人员有用-两种算法(训练和测试)在合成数据集上的相对性能应该与它们在原始数据集上的相对性能(训练和测试时)相同。

英文摘要:

Machine learning has the potential to assist many communities in using the large datasets that are becoming more and more available. Unfortunately, much of that potential is not being realized because it would require sharing data in a way that compromises privacy. In order to overcome this hurdle, several methods have been proposed that generate synthetic data while preserving the privacy of the real data. In this paper we consider a key characteristic that synthetic data should have in order to be useful for machine learning researchers - the relative performance of two algorithms (trained and tested) on the synthetic dataset should be the same as their relative performance (when trained and tested) on the original dataset.

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。

↑