Towards practical data alignment in production federated learning  

作　　者：Yexuan SHI Wei YU Yuanyuan ZHANG Chunbo XUE Yuxiang ZENG Zimu ZHOU Manxue GUO Lun XIN Wenjing NIE 

机构地区：[1]State Key Laboratory of Complex&Critical Software Environment and Advanced Innovation Center for Future Blockchain and Privacy Computing,Beihang University,Beijing 100191,China [2]Zhongguancun Pan Connected Mobile Communication Technology Innovation and Application Research Institute,Beijing 100088,China [3]China Mobile Research Institute,Beijing 100053,China [4]School of Data Science,City University of Hong Kong,Hong Kong 999077,China

出　　处：《Frontiers of Computer Science》2025年第1期167-169,共3页计算机科学前沿(英文版)

基　　金：supported by the National Natural Science Foundation of China(Grant Nos.U21A20516,62076017,and 6233000216);the Beihang University Basic Research Funding(No.YWF-22-L-531);the CCF-Huawei Populus Grove Fund(CCF-HuaweiDB202310).

摘　　要：1 Introduction Federated learning has emerged as a promising par-adigm for collaborative model training that facilitates cooperation among multiple parties while ensuring data privacy[1].Successful alignment of data across parties is crucial for effective federated learning[2].This alignment involves harmonizing heterogeneous data from different parties to identify shared data for joint model training.Private set intersection(PSI)is a technique that allows the alignment of common entities between parties without revealing additional information.However,efficiently performing data alignment with PSI in federated learning[3],especially when dealing with highly unbalanced data,remains challenging due to the low efficiency.

关 键 词：ALIGNMENT dealing PARTIES 

分 类 号：P20[天文地球—测绘科学与技术]