Federated Learning

Ask about this topic

Overview

Federated learning studies how multiple devices or institutions can train models collaboratively while keeping data local, for example across hospitals, phones, or companies. A common approach, FedAvg, aggregates local model updates; related methods use personalization or client clustering, split learning, model compression, and lightweight adapters such as LoRA. Differential privacy and secure aggregation can limit exposure of updates, while robust aggregation and client-selection methods address malicious participants and uneven data or resources. The central challenge is balancing accuracy and fairness across heterogeneous clients with privacy, security, communication cost, and reliable evaluation; keeping data local alone does not guarantee privacy or strong performance.

Latest papers

CardsList

961 papers112 papers in the last four weeks, up 1% on the four weeks before. 0.6% of all new papers.

  1. CovFedAvg: Local Low-Loss Curves and Federated Model Selection

    Oct 29, 2026Federico Lucchetti, Marcus VölpFederated LearningFederated Learning Aggregation

    Center for Psychiatric Neuroscience, Department of Psychiatry, Lausanne University Hospital and the University of Lausanne, Lausanne, Switzerland · Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Luxembourg

  2. Adaptive Federated Optimization Across Smooth and Nonsmooth Regimes

    Oct 29, 2026Zimeng Wang, Ali Dadras, Alp YurtseverFederated LearningAdaptive Gradient Methods

    Department of Mathematics and Mathematical Statistics, Ume˚a University, Sweden

  3. Does Federated Training Degrade Explainability? A Comparative Analysis of Grad-CAM Faithfulness in Centralized vs. Federated Deepfake Detection

    Oct 29, 2026Muhammad Uzair Shahid, Muhammad Zabil MehboobExplainable Deepfake DetectionGradient-Based Attribution

    independent researcher based in Pakistan

  4. Fed-IGTD: A federated learning-based framework for tabular-to-image encoding

    Oct 28, 2026David Chushig-Muzo, Eva Milara, Francisco J. Lara Abelenda +2Federated LearningDifferentially Private Federated Learning

    Department of Signal Theory and Communications, Telematics and Computing Systems, Rey Juan Carlos University (URJC), Madrid, Spain. · Faculty of Experimental Sciences, Universidad Francisco de Vitoria, Madrid, Spain. · Faculty of Engineering, Universidad Latina de Panamá (ULATINA), Panama City, Panama. +1

  5. Communication-Efficient Clustered Federated Learning in Non-IID Wireless Networks

    Oct 28, 2026Martin Isaksson, Rickard Cöster, Šarūnas Girdzijauskas +1Federated LearningClustered Federated Learning

    Ericsson AB and KTH Royal Institute of Technology, Sweden · Ericsson AB, Sweden · KTH Royal Institute of Technology and RISE Research Institutes of Sweden, Sweden

  6. On the Generalization Gap of Streaming Federated Learning with Markovian Data

    Oct 28, 2026Masoud Kavian, Milad Sefidgaran, Youssef Attia El Hili +2Federated LearningOnline Federated Learning

    Huawei Paris Research Center, Huawei Technologies Ltd., France · Huawei Noah’s Ark Lab, Paris, France · Université Gustave Eiffel, France

  7. Governance-Aware Federated Learning for Multi-Agent AI Systems: A Policy-Driven Framework for Trustworthy Collaborative AI

    Oct 28, 2026Kiranmayee Janardhan, Karthick S, Madhusmita Panda +2Federated LearningTrust-Aware Federated Learning

    Responsible AI Office, Infosys Limited, Infosys Avenue, 3rd Cross, Electronic City, Hosur Road, Bengaluru – 560100, Karnataka, India

  8. Data Amount Heterogeneity Improves Performance in Federated Learning for Neuroimaging

    Oct 28, 2026Paul Kurian, Tamoghna Chattopadhyay, Abhijith Shaji +3Federated LearningHeterogeneous Federated Learning

    Information Sciences Institute, University of Southern California, Marina del Rey, CA, USA · Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Marina del Rey, CA, USA · University of California, Riverside, CA, USA

  9. Federated Learning for Semantic Communications over Multiple Access Channels

    Oct 27, 2026Yalin E. Sagduyu, Tugba Erpek, Yi ShiSemantic CommunicationWireless Communications

    Nexcepta, Gaithersburg, MD, USA · Virginia Tech, Arlington, VA, USA

  10. Information-Theoretic Secure Aggregation With Heterogeneous Client Quantization

    Oct 26, 2026Shreya Meel, Sennur Ulukus, Itzhak TamoPrivacy-Preserving Federated LearningFederated Learning Aggregation

    Department of Electrical and Computer Engineering, University of Maryland, College Park, MD, USA · Department of Electrical Engineering, Tel Aviv University, Tel Aviv, Israel

  11. SCAFFOLD under Hessian Similarity: Sharp Convergence Rates

    Oct 26, 2026Zhirayr Tovmasyan, Slavomír Hanzely, Egor Shulgin +2Federated LearningHeterogeneous Federated Learning

    King Abdullah University of Science and Technology (KAUST) · CISPA Helmholtz Center for Information Security · Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)

  12. Pricing Cross-Bank Context in Federated Anti-Money Laundering

    Oct 26, 2026Lidia Losavio, Dario Fenoglio, Martin Gjoreski +1Anti-Money Laundering DetectionFederated Graph Learning

    Università della Svizzera italiana (USI), Lugano, Switzerland

  13. Self-Supervised Pretraining for PHM: What Transfers, What Does Not, and What Federating It Costs

    Oct 26, 2026José Sanz-Durán, David Solís-MartínSelf-Supervised Pre-TrainingPredictive Maintenance

    Department of Computer Science and Artificial Intelligence, Universidad de Sevilla, Seville, Spain

  14. One-Shot Federated Model Editing for Device Dynamics at the Edge

    Oct 26, 2026Youming Tao, Weijun Yin, Huanyi Xie +5Federated LearningFederated Unlearning

    School of Electrical Engineering and Computer Science, TU Berlin, 10623 Berlin, Germany · School of Cyber Science and Technology, Beihang University, Beijing 100191, China · Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University, Beijing 100083, China +2

  15. Efficient Exact Unlearning for Federated Zeroth-Order Optimization

    Oct 26, 2026Weijun Yin, Yanqing Yao, Falko Dressler +2Federated UnlearningFederated Learning

    School of Cyber Science and Technology, Beihang University, Beijing 100191, China · Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University, Beijing 100083, China · School of Electrical Engineering and Computer Science, TU Berlin, 10623 Berlin, Germany +1

  16. Fed-MAPTrack: Federated Modality-aware Prompt Tuning for RGB-X Tracking

    Oct 26, 2026Xiangyu Liu, Yijie Shen, Yue Yin +3Multimodal Visual Object TrackingMultimodal Federated Learning

    Beijing Normal-Hong Kong Baptist University, 519087, Zhuhai, Guangdong, China · Zhejiang University, 310058, Hangzhou, Zhejiang, China · Peking University, 100871, Beijing, China +1

  17. Fed-Universe: A Semantic-Geometric-Topological-Human (S-G-T-H) Stack for Negotiated Alignment in Federated Systems

    Oct 25, 2026Ting Xu, Henry LeungFederated LearningHeterogeneous Federated Learning

    Department of Biomedical Engineering, University of Calgary, Calgary, Canada · Department of Electrical and Software Engineering, University of Calgary, Calgary, Canada

  18. Hessian-Similar Optimization with Capped Participation: Lower Bounds and Virtual Masters

    Oct 24, 2026Rui WangFederated LearningVariance Reduction

    Microsoft, Vancouver, BC, Canada

  19. Projection-Based Federated Learning on Compact Submanifolds with Geometry-Independent Differential Privacy

    Oct 24, 2026Thibault Pautrel, Florent Bouchard, Guillaume Ginolhac +2Differentially Private Federated LearningFederated Learning

    Université Paris-Saclay, CentraleSupélec, L2S, Gif-sur-Yvette, France · Université Paris-Saclay, CNRS, CentraleSupélec, L2S, Gif-sur-Yvette, France · Université Savoie Mont Blanc, LISTIC, Annecy, France +1

  20. Geodesic-SVDD Latent Mixup for One-Shot Distributed Tabular Learning

    Oct 24, 2026Andrea Moleri, Christian Internò, Markus Olhofer +2Federated LearningTabular ML

    Honda Research Institute Europe · University of Milan-Bicocca · Bielefeld University

  21. Clean-label Poisoning Attack and Defense Game for Federated Learning in Vehicular Networks

    Oct 23, 2026Yalin E. Sagduyu, Tugba Erpek, Nathan Stephenson +1Federated LearningIntelligent Transportation Systems

    Nexcepta Inc., Gaithersburg, MD, USA · RTX BBN Technologies, Cambridge, MA, USA

  22. Democratizing LLM Training with the Edge: Challenges, Systems, and the Road Ahead

    Oct 23, 2026Ziyue Luo, Jiaxuan Cai, Cedric LeDenmat +27LLM TrainingDistributed Training

    The Ohio State University · University of Wisconsin–Madison · Rochester Institute of Technology +5

  23. Federated Nonparametric Regression with Heterogeneous Clients

    Oct 23, 2026Xiaoran Jiang, Anand N. VidyashankarFederated LearningNonparametric Regression

  24. Evolving Federated Density Peak Clustering with Shuffler-Based Anonymization

    Oct 22, 2026Miha Ožbot, Seiichi Ozawa, Igor ŠkrjancClusteringFederated Learning

    Faculty of Electrical Engineering, University of Ljubljana, Tržaška cesta 25, Ljubljana, 1000, Slovenia. · Center for Mathematical and Data Sciences, Kobe University, 1-1 Rokkodai-cho, Nada-ku, Kobe, 657-8501, Japan.

  25. Is High Local Accuracy Enough? Geometric Consensus with Support-Adaptive Statistical Personalization for Federated Learning

    Oct 22, 2026Junyu Lin, Bosong Qi, Pengcheng Shi +1Federated LearningHeterogeneous Federated Learning

    School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430072, China

  26. One-shot federated unsupervised domain adaptation with Smoothed Knowledge Distillation and teacher refinement

    Oct 22, 2026Ali Abedi, Q. M. Jonathan Wu, Ning Zhang +1Unsupervised Domain AdaptationFederated Learning

    University of Windsor, Department of Electrical and Computer Engineering · Queen’s University, Department of Electrical and Computer Engineering

  27. FedBST: Bilateral Self-Training for Unsupervised Federated Classification

    Oct 22, 2026Aijing Yu, Kuangpu Guo, Jian Liang +1Federated LearningSelf-Training

    School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China · Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China · NLPR & MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China +2

  28. From Classifier Heads to Encoder Prototypes: Personalized Federated Learning with Head-Derived Clustering

    Oct 21, 2026Amirardalan Dehghanpour, Arian Noori, Ehsan Tanghatari +2Federated LearningNon-IID Federated Learning

    Sharif University of Technology · Tehran Institute for Advanced Studies (TeIAS)

  29. Extending FAIR Principles with Observability for Trustworthy Federated Learning

    Oct 21, 2026Hangli Ge, Noboru KoshizukaTrust-Aware Federated LearningFederated Learning

    Interfaculty Initiative in Information Studies; The University of Tokyo

  30. Discount Yourself: Self-inclusive Freshness-weighted Gossip for Decentralised Learning under Client Outages

    Oct 20, 2026Qiyuan Wang, Ke Xiao, Christos AnagnostopoulosFederated Learning AggregationDecentralized Learning

    University of Glasgow