联邦忘却学习研究综述  

A Survey on Federated Unlearning

作　　者：王鹏飞 魏宗正[1,2] 周东生 宋威[1,2] 肖蕴明 孙庚[5,6] 于硕 张强[1,2] WANG Peng-Fei;WEI Zong-Zheng;ZHOU Dong-Sheng;SONG Wei;XIAO Yun-Ming;SUN Geng;YU Shuo;ZHANG Qiang(School of Computer Science and Technology,Dalian University of Technology,Dalian,Liaoning 116024;Key Laboratory of Social Computing and Cognitive Intelligence(Dalian University of Technology)Ministry of Education,Dalian,Liaoning 116024;Key Laboratory of Advanced Design and Intelligent Computing(Ministry of Education),Dalian University,Dalian,Liaoning 116024;Department of Computer Science,Northwestern University,Evanston 60208 USA;School of Computer Science and Technology,Jilin University,Changchun 130012;Key Laboratory of Symbolic Computing and Knowledge Engineering(Ministry of Education)Jilin University,Changchun 130012)

机构地区：[1]大连理工大学计算机科学与技术学院,辽宁大连116024 [2]大连理工大学社会计算与认知智能教育部重点实验室,辽宁大连116024 [3]大连大学先进设计与智能计算教育部重点实验室,辽宁大连116622 [4]美国西北大学计算机科学系,美国埃文斯顿60208 [5]吉林大学计算机科学与技术学院,长春130012 [6]吉林大学符号计算与知识工程教育部重点实验室,长春130012

出　　处：《计算机学报》2024年第2期396-422,共27页Chinese Journal of Computers

基　　金：国家重点研发计划(2021ZD0112400);国家自然科学基金联合基金项目(U1908214);国家自然科学基金青年项目(62202080);中国博士后科学基金面上项目(2023M733354);中央高校基本科研业务费(DUT23YG122)资助.

摘　　要：数据已经成为与土地、劳动力、资本、技术等并列的重要生产要素之一.利用数据分析挖掘数据的潜在价值,有助于推动产业创新、技术升级和区域经济发展.然而,在数据使用过程中,隐私泄露等风险限制了数据的流通和共享.因此,如何在数据流通和共享过程中保护数据隐私已成为研究热点.联邦忘却学习(Federated Un-learning)撤销用户数据对联邦学习模型的训练更新,可以进一步保护联邦学习用户的数据安全.本文综述了联邦忘却学习的研究工作,首先简要阐述了联邦学习架构,并引出忘却学习和联邦忘却学习的概念和定义;其次,根据修正对象的不同将联邦忘却学习算法分为面向全局模型和面向局部模型两类,并详细分析各类算法的实现细节以及优缺点;然后,本文还详述联邦忘却学习中常用评价指标,将评价指标划分为模型表现指标、遗忘效果指标和隐私保护指标三类,并分析不同类型评价指标的优缺点;最后,本文对联邦忘却学习未来的研究方向进行展望.Data has become an important factor of production alongside land,labor,capital,technology,etc.By leveraging data analysis to mine potential value,we can uncover profound insights into consumer behavior,market trends,and production efficiency,thereby promoting industrial innovation,technology upgrades,and regional economic development.However,it may cause privacy leakage problems when we use and share data.This oversight has also led to more serious issues,such as the leakage of sensitive data and illegal cross-border data transfers.For instance,some financial companies,due to the absence of comprehensive privacy protection mechanisms in the processes of collecting,circulating,and utilizing user data,have experienced incidents where data is used and traded without user consent.As a result,it severely stops the data circulation and sharing.To further protect user data privacy,federated unlearning can rollback the data-generated training updates to the machine learning model,which can further protect the data privacy and security of users.In this paper,we review the research work of federated unlearning.Firstly,we conduct an in-depth analysis of the federated learning training architecture,highlighting the specific types of privacy leakage threats.To reduce the risk of privacy leaks,we introduce the concept and definition of unlearning,and list different unlearning scenarios,thereby seamlessly transitioning to the concept of federated unlearning.On this basis,we outline the processes involved in federated unlearning and introduce unlearning granularity and challenges.Secondly,the federated unlearning algorithms are divided into two categories,including global model-oriented and local model-oriented algorithms according to the modified object.We further subdivide into several subcategories based on two major categories and analyze the implementation details of each algorithm in depth.To further compare the strengths and weaknesses,we conduct detailed comparative analyses across different categories of algorithms,focu

关 键 词：联邦学习 联邦忘却学习 数字经济 隐私保护 边缘智能 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]