传统的联邦学习（FL）方法假设客户端是协作的，目标一致，共同致力于一个共享的全局模型。然而，在许多现实场景中，客户端表现为具有各自目标和策略行为的理性参与者，而现有FL框架无法充分应对这一概念。为弥合这一差距，我们提出了多人联邦学习（Multiplayer Federated Learning，MpFL），这是一个新颖的框架，将FL环境中的客户端建模为博弈论背景下的参与者，旨在达到均衡。在这种场景下，每个参与者都试图优化自己的效用函数，该效用函数可能与集体目标不一致。在MpFL框架内，我们提出了逐参与者局部随机梯度下降（Per-Player Local Stochastic Gradient Descent，PEARL-SGD）算法，在该算法中，每个参与者/客户端独立执行局部更新，并周期性地与其他参与者通信。我们从理论上分析了PEARL-SGD，并证明在随机设置下，与其非局部对应方法相比，该算法能以更少的通信达到均衡的邻域。最后，我们通过数值实验验证了我们的理论发现。
英文摘要：
Traditional Federated Learning (FL) approaches assume collaborative clients with aligned objectives working towards a shared global model. However, in many real-world scenarios, clients act as rational players with individual objectives and strategic behaviors, a concept that existing FL frameworks are not equipped to adequately address. To bridge this gap, we introduce Multiplayer Federated Learning (MpFL), a novel framework that models the clients in the FL environment as players in a game-theoretic context, aiming to reach an equilibrium. In this scenario, each player tries to optimize their own utility function, which may not align with the collective goal. Within MpFL, we propose Per-Player Local Stochastic Gradient Descent (PEARL-SGD), an algorithm in which each player/client performs local updates independently and periodically communicates with other players. We theoretically analyze PEARL-SGD and prove that it reaches a neighborhood of equilibrium with less communication in the stochastic setup compared to its non-local counterpart. Finally, we verify our theoretical findings through numerical experiments.
The Future of Digital Health with Federated Learning
NVIDIA（英伟达）；Technical University of Munich (TUM)（慕尼黑工业大学）；ETH Zürich（苏黎世联邦理工学院）；University of Pennsylvania (UPenn)（宾夕法尼亚大学）；Owkin；Vanderbilt University Medical Center（范德比尔特大学医学中心）；German Cancer Research Center (DKFZ)（德国癌症研究中心）；King’s College London (KCL)（伦敦国王学院）；Intel Corporation（英特尔公司）；Clinical Center, National Institutes of Health (NIH)（美国国立卫生研究院临床中心）；OpenMined；University of Oxford（牛津大学）
Communication-Efficient Federated Learning by Exploiting Spatio-Temporal Correlations of Gradients
College of Information Science and Technology, Jinan University（信息科学与技术学院，暨南大学）；College of Engineering, Mathematics and Physical Sciences, University of Exeter（工程、数学与物理科学学院，埃克塞特大学）
Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Sampling
Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳市人工智能与机器人研究院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；IBM T. J. Watson Research Center（IBM托马斯·J·沃森研究中心）；Yale University（耶鲁大学）
Colorectal Cancer Histopathological Grading using Multi-Scale Federated Learning
Department of Computer Science and Engineering, European University of Bangladesh（欧洲 bangladesh 大学 计算机科学与工程系）；Department of Computer Science and Engineering , BRAC University,Dhaka, Bangladesh（brac 大学 计算机科学与工程系）；Department of Computer Science and Engineering , Daffodil International University, Dhaka, Bangladesh（daffodil 国际大学 计算机科学与工程系）；Department of Institute of Information Technology, University of Dhaka, Bangladesh（达卡大学 信息科技学院）；Department of Computer Science and Engineering , BRAC University,Dhaka（brac 大学 计算机科学与工程系）；Ochsner Center for Outcomes Research, Ochsner Research, New Orleans, LA 70121, USA（ochsner 成果研究中心，ochsner 研究）
A Federated Learning Framework for Stenosis Detection
Università Politecnica delle Marche（马尔凯理工大学）；Università degli Studi di Macerata（马切拉塔大学）；Azienda Ospedaliero Universitaria delle Marche（马尔凯大学医院）；Ospedale del Mare, ASL NA 1（ASL NA 1 海洋医院）；University of Macerata（马切拉塔大学）；Scuola Superiore Sant’Anna（圣安娜高等研究学院）
SemiSFL: Split Federated Learning on Unlabeled and Non-IID Data
School of Computer Science and Technology, University of Science and Technology of China（中国科学技术大学计算机科学与技术学院）；Suzhou Institute for Advanced Research, University of Science and Technology of China（中国科学技术大学苏州高等研究院）；Department of Computer Science and Engineering, University at Buffalo, the State University of New York（纽约州立大学布法罗分校计算机科学与工程系）
Bandwidth-Aware and Overlap-Weighted Compression for Communication-Efficient Federated Learning
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Hong Kong Baptist University（香港浸会大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））
FLAT: Revealing Hidden Latent-Conditioned Backdoor Failures in Federated Learning
College of Engineering and Computer Science, VinUniversity（VinUniversity工程与计算机科学学院）；VinUni-Illinois Smart Health Center, VinUniversity（VinUniversity-VinUni-Illinois智能健康中心）；Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校Siebel计算与数据科学学院）；Faculty of Computer Science and Information Technology, Universiti Malaya（马来亚大学计算机科学与信息技术学院）
