ACCEL: an efflcient and privacy-preserving federated logistic regression scheme over vertically partitioned data  

作　　者：Jiaqi ZHAO Hui ZHU Fengwei WANG Rongxing LU Hui LI Zhongmin ZHOU Haitao WAN 

机构地区：[1]State Key Laboratory of Integrated Networks Services,Xidian University,Xi’an 710071,China [2]Faculty of Computer Science,University of New Brunswick,Fredericton E3B 5A3,Canada [3]China Mobile(Suzhou)Software Technology Co.,Ltd.,Suzhou 215153,China

出　　处：《Science China(Information Sciences)》2022年第7期94-95,共2页中国科学（信息科学）（英文版）

基　　金：supported by National Key R&D Program of China (Grant No. 2021YFB3101300);National Natural Science Foundation of China (Grant Nos.61972304, 61932015);Science Foundation of the Ministry of Education (Grant No. MCM20200101)。

摘　　要：Dear editor,With the age of big data coming, massive data are being generated distributedly all the time and stored as the form of data islands;meanwhile, data privacy and security are strengthened with the introduction of some privacy laws, which thus bring huge challenges to traditional centralized machine learning. Consequently, federated learning(FL) [1], which can construct global machine learning models over multiple participants while keeping their data localized, gains widespread attention and shows its vast prospects in many fields [2].

关 键 词：STRENGTHENED MASSIVE WIDESPREAD 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论] TP309[自动化与计算机技术—计算机科学与技术]