Adaptive Dual-Weighting Framework for Federated Learning via Out-of-Distribution Detection
School of Software Technology, Zhejiang University(浙江大学软件技术学院);Zhejiang Key Laboratory of Digital-Intelligence Service Technology(浙江省数字智能服务技术重点实验室);School of Information Technology and Artificial Intelligence, Zhejiang University of Finance and Economics(浙江财经大学信息科技与人工智能学院);College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);School of Intelligent Systems Engineering, Sun Yat-sen University(中山大学智能系统工程学院);Department of Electrical and Computer Engineering, New Jersey Institute of Technology(新泽西理工学院电子与计算机工程系)
Federated Learning (FL) enables collaborative model training across large-scale distributed service nodes while preserving data privacy, making it a cornerstone of intelligent service systems in edge-cloud environments. However, in real-world service-oriented deployments, data generated by heterogeneous users, devices, and application scenarios are inherently non-IID. This severe data heterogeneity critically undermines the convergence stability, generalization ability, and ultimately the quality of service delivered by the global model. To address this challenge, we propose FLood, a novel FL framework inspired by out-of-distribution (OOD) detection. FLood dynamically counteracts the adverse effects of heterogeneity through a dual-weighting mechanism that jointly governs local training and global aggregation. At the client level, it adaptively reweights the supervised loss by upweighting pseudo-OOD samples, thereby encouraging more robust learning from distributionally misaligned or challenging data. At the server level, it refines model aggregation by weighting client contributions according to their OOD confidence scores, prioritizing updates from clients with higher in-distribution consistency and enhancing the global model's robustness and convergence stability. Extensive experiments across multiple benchmarks under diverse non-IID settings demonstrate that FLood consistently outperforms state-of-the-art FL methods in both accuracy and generalization. Furthermore, FLood functions as an orthogonal plug-in module: it seamlessly integrates with existing FL algorithms to boost their performance under heterogeneity without modifying their core optimization logic. These properties make FLood a practical and scalable solution for deploying reliable intelligent services in real-world federated environments.
Conformal Prediction for Federated Uncertainty Quantification Under Label Shift
Ecole Polytechnique(巴黎综合理工学院);Lagrange Mathematics and Computing Research Center(拉格朗日数学与计算研究中心);Skolkovo Institute of Science and Technology(斯科尔科沃科学技术研究院);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);Technology Innovation Institute(技术创新研究院)
FedImp: Enhancing Federated Learning Convergence with Impurity-Based Weighting
School of Information and Communication Technology (SOICT), Hanoi University of Science and Technology (HUST)(河内科技大学信息与通信技术学院);School of Science, Engineering and Technology, Penn State Harrisburg, The Pennsylvania State University(宾夕法尼亚州立大学哈里斯堡分校科学、工程与技术学院)
Institute for Predictive Deep Learning in Medicine and Healthcare, Justus-Liebig University(尤斯图斯-李比希大学医学与医疗保健预测深度学习研究所);Institute for Medical Informatics, University Medical Center Göttingen(哥廷根大学医学中心医学信息学研究所)
Byzantine-Resilient Over-the-Air Federated Learning under Zero-Trust Architecture
Southeast University(东南大学);Purple Mountain Laboratories(紫金山实验室);Zhejiang Lab(之江实验室);Zhejiang University(浙江大学);University of California at Irvine(加州大学欧文分校);Nanyang Technological University(南洋理工大学)
University of British Columbia(英属哥伦比亚大学);Baidu Research(百度研究院)
我们研究联邦优化问题从一个双重的角度来看,并提出了一个新的算法称为联邦双坐标下降(FedDCD),这是基于一种类型的坐标下降方法开发的Necora等人。[Journal of Optimization Theory and Applications,2017]。此外,我们加强了FedDCD方法与不精确的梯度预言和Nesterov的加速。我们从理论上证明,我们提出的方法实现了更好的收敛速度比国家的最先进的原始联邦优化算法在某些情况下。真实世界数据集上的数值实验支持我们的分析。
Personalized Federated Learning for Spatio-Temporal Forecasting: A Dual Semantic Alignment-Based Contrastive Approach
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
Combating Data Imbalances in Federated Semi-supervised Learning with Dual Regulators
The Hong Kong University of Science and Technology(香港科技大学);SenseTime Research(商汤科技研究院);Sony AI(索尼人工智能);The Hong Kong Polytechnic University(香港理工大学);Northwestern Polytechnical University(西北工业大学)
DP2FL: Dual Prompt Personalized Federated Learning in Foundation Models
College of Software, Jilin University(吉林大学软件学院);College of Computer Science and Technology, Jilin University(吉林大学计算机科学与技术学院);College of Computer Science and Engineering, Changchun University of Technology(长春理工大学计算机科学与工程学院)
FedSiam-DA: Dual-aggregated Federated Learning via Siamese Network under Non-IID Data
Qilu University of Technology (Shandong Academy of Sciences)(齐鲁工业大学(山东省科学院));Shandong Computer Science Center(山东省计算中心);Guizhou University(贵州大学);Zhejiang University(浙江大学)
GuardFed: A Trustworthy Federated Learning Framework Against Dual-Facet Attacks
School of Artificial Intelligence and Computer Science, Nantong University(人工智能与计算机科学学院,南通大学);School of Electrical and Computer Engineering, The University of Sydney(电气与计算机工程学院,悉尼大学);School of Computer Science, University of St Andrews(计算机科学学院,圣安德鲁斯大学);Faculty of Data Science, City University of Macau(数据科学学院,澳门城市大学);Department of Electrical and Computer Engineering, University of Alberta(电气与计算机工程学院,阿尔伯塔大学)
Dual-Segment Clustering Strategy for Hierarchical Federated Learning in Heterogeneous Wireless Environments
College of Electronics and Information Engineering, Tongji University(同济大学电子与信息工程学院);Tongji Hospital, Tongji University(同济大学附属同济医院);Data61, CSIRO(澳大利亚联邦科学与工业研究组织Data61研究院);Guangzhou Huatu Information Technology Co., Ltd.(广州华图信息技术有限公司);School of Electrical and Computer Engineering, The University of Sydney(悉尼大学电气与计算机工程学院)
FedSPM: Routing-Enabled Federated Learning under Dual Heterogeneity via Semiparametric Mixture
Institute of Statistics and Big Data, Renmin University of China(中国人民大学统计与大数据研究院);Department of Statistics and Actuarial Science, University of Waterloo(滑铁卢大学统计与精算科学系)
Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data
School of Artificial Intelligence, Beihang University(北京航空航天大学人工智能学院);School of Computer Science and Technology, Shandong University(山东大学计算机科学与技术学院);Center for Applied Statistics, School of Statistics, Renmin University of China(中国人民大学统计学院应用统计中心);Beijing Academy of Blockchain and Edge Computing(北京区块链与边缘计算研究院);Department of Statistics, Fudan University(复旦大学统计系);Department of Computer Science and Engineering, Hong Kong University of Science and Technology(香港科技大学计算机科学与工程系)