Fair Concurrent Training of Multiple Models in Federated Learning
Information Systems Technology and Design Pillar, Singapore University of Technology and Design(新加坡科技设计大学信息系统技术与设计学院);Electrical and Computer Engineering, Carnegie Mellon University(卡内基梅隆大学电子与计算机工程学院);Electrical and Computer Engineering, Northeastern University(东北大学电子与计算机工程学院)
Marie Siew, Haoran Zhang, Jong-Ik Park, Yuezhou Liu, Yichen Ruan, Lili Su, Stratis Ioannidis, Edmund Yeh, Carlee Joe-Wong
备注:
Accepted at IEEE Transactions on Networking (TON) 2025
Federated learning (FL) enables collaborative learning across multiple clients. In most FL work, all clients train a single learning task. However, the recent proliferation of FL applications may increasingly require multiple FL tasks to be trained simultaneously, sharing clients' computing and communication resources, which we call Multiple-Model Federated Learning (MMFL). Current MMFL algorithms use naive average-based client-task allocation schemes that can lead to unfair performance when FL tasks have heterogeneous difficulty levels, e.g., tasks with larger models may need more rounds and data to train. Just as naively allocating resources to generic computing jobs with heterogeneous resource needs can lead to unfair outcomes, naive allocation of clients to FL tasks can lead to unfairness, with some tasks having excessively long training times, or lower converged accuracies. Furthermore, in the FL setting, since clients are typically not paid for their training effort, we face a further challenge that some clients may not even be willing to train some tasks, e.g., due to high computational costs, which may exacerbate unfairness in training outcomes across tasks. We address both challenges by firstly designing FedFairMMFL, a difficulty-aware algorithm that dynamically allocates clients to tasks in each training round. We provide guarantees on airness and FedFairMMFL's convergence rate. We then propose a novel auction design that incentivizes clients to train multiple tasks, so as to fairly distribute clients' training efforts across the tasks. We show how our fairness-based learning and incentive mechanisms impact training convergence and finally evaluate our algorithm with multiple sets of learning tasks on real world datasets.
FUSE: Fairness-aware Update Screening against Byzantine Exploitation in $q$-Fair Federated Learning
George Mason University(乔治梅森大学);The University of Hong Kong(香港大学);Huazhong University of Science and Technology(华中科技大学);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));The Hong Kong Polytechnic University(香港理工大学)
Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversity
National Engineering Research Center for Multimedia Software(国家多媒体软件工程技术研究中心);School of Computer Science, Wuhan University(武汉大学计算机学院);Taikang Center for Life and Medical Sciences, Wuhan University(武汉大学泰康生命医学中心)
FedPF: Accurate Target Privacy Preserving Federated Learning Balancing Fairness and Utility
The School of Computer Science, Shanghai Jiao Tong University, Shanghai, China(上海交通大学计算机科学学院,上海,中国);The Shanghai Key Laboratory of Integrated Administration Technologies for Information Security, Shanghai, China(上海信息安全集成管理技术重点实验室,上海,中国);The School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, China(香港中文大学(深圳)科学与工程学院,中国)
Improving Fairness for Data Valuation in Horizontal Federated Learning
University of British Columbia(不列颠哥伦比亚大学);Huawei Technologies Canada Co.(华为技术加拿大公司);Simon Fraser University(西蒙弗雷泽大学);KTH Royal Institute of Technology(KTH皇家理工学院)
Fairness-Aware Job Scheduling for Multi-Job Federated Learning
Nanyang Technological University(南洋理工大学);DSO National Laboratories(DSO国家实验室);Alibaba Group(阿里巴巴集团);Alibaba-NTU Singapore Joint Research Institute(阿里巴巴-新加坡南洋理工大学联合研究院)
Fairness-Aware Client Selection for Federated Learning
Nanyang Technological University (NTU)(南洋理工大学);Alibaba-NTU Singapore Joint Research Institute(阿里巴巴-新加坡南洋理工大学联合研究院);Alibaba Group(阿里巴巴集团);University of Science and Technology of China(中国科学技术大学)
FairFML: Fair Federated Machine Learning with a Case Study on Reducing Gender Disparities in Cardiac Arrest Outcome Prediction
Duke-NUS Medical School(杜克-新加坡国立大学医学院);Duke University(杜克大学);Kyoto University(京都大学);Singapore Health Services(新加坡保健服务);Singapore General Hospital(新加坡中央医院);NUS Artificial Intelligence Institute(新加坡国立大学人工智能研究所);National University of Singapore(新加坡国立大学)
FAIRVAR: Fair Federated Learning via Variance Regularization
Department of Computing Science, Umeå University, Umeå, Sweden(计算机科学系,乌梅大学,乌梅,瑞典);Department of Mathematics and Mathematical Statistics, Umeå University, Umeå, Sweden(数学与统计学系,乌梅大学,乌梅,瑞典)
Towards Collaborative Fairness in Federated Learning Under Imbalanced Covariate Shift
The Pennsylvania State University(宾夕法尼亚州立大学);State University of New York at Albany(纽约州立大学阿尔巴尼分校);University of Minnesota Twin Cities(明尼苏达大学双城分校);Dalian University of Technology(大连理工大学)
Towards Fair and Privacy-Preserving Federated Deep Models
National University of Singapore(新加坡国立大学);Monash University(莫纳什大学);IBM Singapore Lab(IBM新加坡实验室);The University of Melbourne(墨尔本大学);Swinburne University of Technology(斯威本科技大学);Nanyang Technological University(南洋理工大学);Australian National University(澳大利亚国立大学)