当前位置:
X-MOL 学术
›
J. Am. Med. Inform. Assoc.
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Fold-stratified cross-validation for unbiased and privacy-preserving federated learning.
Journal of the American Medical Informatics Association ( IF 6.4 ) Pub Date : 2020-07-04 , DOI: 10.1093/jamia/ocaa096 Romain Bey 1 , Romain Goussault 2 , François Grolleau 1 , Mehdi Benchoufi 1 , Raphaël Porcher 1
Journal of the American Medical Informatics Association ( IF 6.4 ) Pub Date : 2020-07-04 , DOI: 10.1093/jamia/ocaa096 Romain Bey 1 , Romain Goussault 2 , François Grolleau 1 , Mehdi Benchoufi 1 , Raphaël Porcher 1
Affiliation
We introduce fold-stratified cross-validation, a validation methodology that is compatible with privacy-preserving federated learning and that prevents data leakage caused by duplicates of electronic health records (EHRs).
中文翻译:
折叠分层交叉验证,可实现无偏见和隐私保护的联合学习。
我们引入了折叠分层交叉验证,该验证方法与保留隐私的联合学习兼容,并且可以防止由于重复电子健康记录(EHR)而导致数据泄漏。
更新日期:2020-09-10
中文翻译:
折叠分层交叉验证,可实现无偏见和隐私保护的联合学习。
我们引入了折叠分层交叉验证,该验证方法与保留隐私的联合学习兼容,并且可以防止由于重复电子健康记录(EHR)而导致数据泄漏。