Federated Learning (FL) is a distributed machine learning strategy, developed for settings where training data is owned by distributed devices and cannot be shared. FL circumvents this constraint by carrying out model training in distribution. The parameters of these local models are shared intermittently among participants and aggregated to enhance model accuracy. This strategy has been rapidly adopted by the industry in efforts to overcome privacy and resource constraints in model training. However, the application of FL to real-world settings brings additional challenges associated with heterogeneity between participants. Research into mitigating these difficulties in FL has largely focused on only two types of heterogeneity: the unbalanced distribution of training data, and differences in client resources. Yet more types of heterogeneity are becoming relevant as the capability of FL expands to cover more complex problems, from the tuning of LLMs to enabling machine learning on edge devices. In this work, we discuss a novel type of heterogeneity that is likely to become increasingly relevant in future applications: this is preference heterogeneity, emerging when clients learn under multiple objectives, with different importance assigned to each objective on different clients. In this work, we discuss the implications of this type of heterogeneity and propose FedPref, a first algorithm designed to facilitate personalised FL in this setting. We demonstrate the effectiveness of the algorithm across different problems, preference distributions and model architectures. In addition, we introduce a new analytical point of view, based on multi-objective metrics, for evaluating the performance of FL algorithms in this setting beyond the traditional client-focused metrics. We perform a second experimental analysis based in this view, and show that FedPref outperforms compared algorithms.
Federated Variational Preference Alignment with Gumbel-Softmax Prior for Personalized User Preferences
Graduate School of AI, POSTECH, Pohang, Republic of Korea(POSTECH人工智能研究生院);Department of CSE, POSTECH, Pohang, Republic of Korea(POSTECH计算机科学与工程系);National AI Research Lab, Seoul, Republic of Korea(首尔国家人工智能研究实验室)
Rethinking Personalized Reward Modeling for LLMs under Preference Heterogeneity via Group-Debiased Federated Learning
Institute of Engineering Research, Korea University(韩国大学工程研究所);Kim Jaechul Graduate School of AI, KAIST(韩国科学技术院金在哲人工智能研究生院);Industrial Management Engineering, Korea University(韩国大学产业管理工程学院)
PPA: Preference Profiling Attack Against Federated Learning
Nanjing University of Science and Technology(南京理工大学);Institute of Information Engineering, Chinese Academy of Science(中国科学院信息工程研究所);Data61, CSIRO(澳大利亚联邦科学与工业研究组织Data61);University of Chinese Academy of Science(中国科学院大学)
Learning Heterogeneous Performance-Fairness Trade-offs in Federated Learning
Department of Computer Science and Engineering and the Research Institute of Trustworthy Autonomous Systems at Southern University of Science and Technology(计算机科学与工程系和可信自主系统研究 institute at 南方科技大学)
FedMint: Intelligent Bilateral Client Selection in Federated Learning with Newcomer IoT Devices
Lebanese American University(黎巴嫩美国大学);Polytechnique Montréal(蒙特利尔理工学院);Khalifa University(哈利法大学);Zayed University(扎耶德大学);New York University(纽约大学);Mohammad Bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
FedTune: Automatic Tuning of Federated Learning Hyper-Parameters from System Perspective
University of California, Davis(加州大学戴维斯分校);The Ohio State University(俄亥俄州立大学);Michigan State University(密歇根州立大学);DEVCOM Army Research Laboratory(DEVCOM陆军研究实验室)
Enhancing Mutual Trustworthiness in Federated Learning for Data-Rich Smart Cities
Mohammad Bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);Polytechnique Montréal(蒙特利尔理工学院);Lebanese American University(黎巴嫩美国大学);Khalifa University(哈利法大学);New York University(纽约大学);Technology Innovation Institute (TII)(技术创新研究所)
FedSKC: Federated Learning with Non-IID Data via Structural Knowledge Collaboration
School of Computing and Information Technology, University of Wollongong, Wollongong, Australia(1 计算与信息科技学院,沃林根大学,澳大利亚);School of Electrical and Computer Engineering, The University of Sydney, Sydney, Australia(2 电气与计算机工程学院,悉尼大学,澳大利亚);School of Cyber Engineering, Xidian University, Xi’an, China(3 网络工程学院,西安电子科技大学,中国);QLD Alliance for Agriculture and Food, The University of Queensland, Brisbane, Australia(4 女王艾丽丝州农业与食品联盟,昆士兰大学,澳大利亚);Principal Research Scientist, CSIRO Data61, Eveleigh, Australia(5 主要研究员,CSIRO Data61,澳大利亚)
Design of Two-Level Incentive Mechanisms for Hierarchical Federated Learning
Nanjing University of Science and Technology(南京理工大学);Hainan University(海南大学);The Hong Kong Polytechnic University(香港理工大学);East China Normal University(华东师范大学);Shanghai Jiao Tong University(上海交通大学)
A Systematic Survey on Federated Sequential Recommendation
School of Computer Science and Technology, Huazhong University of Science and Technology(华中科技大学计算机科学与技术学院);The Hong Kong Polytechnic University(香港理工大学)
FedFlex: Federated Learning for Diverse Netflix Recommendations
Vrije Universiteit Amsterdam Netherlands;Georgia Institute of Technology Mexico;Centrum Wiskunde \& Informatica Netherlands;Georgia Institute of Technology
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)
FedPOIRec: Privacy Preserving Federated POI Recommendation with Social Influence
Institute for Language and Speech Processing, Athena Research Center(雅典娜研究中心语言与语音处理研究所);Department of Electrical and Computer Engineering, Democritus University of Thrace(色雷斯德谟克利特大学电气与计算机工程系)
Structure-Aware Distributed Backdoor Attacks in Federated Learning
Faculty of Applied Sciences, Macao Polytechnic University(应用科学学院,澳门理工学院);Faculty of Cyberspace Security, Software Engineering Institute of Guangzhou(网络安全学院,广州软件工程研究院);School of Engineering and Technology, Central Queensland University(工程与技术学院,中央昆士兰大学);Faculty of Software and Artificial Intelligence, Software Engineering Institute of Guangzhou(软件与人工智能学院,广州软件工程研究院)
FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data
University of Electronic Science and Technology of China(电子科技大学);Angelalign Technology Inc(时代天使科技有限公司);Zhejiang University(浙江大学);IHPC, Agency for Science, Technology and Research, Singapore(新加坡科技研究局信息通信研究院);CFAR, Agency for Science, Technology and Research, Singapore(新加坡科技研究局计算科学与工程中心);Singapore University of Technology and Design(新加坡科技设计大学)