Expanding the Reach of Federated Learning by Reducing Client Resource Requirements
Not on the map. Why?
Abstract (arXiv)
Communication on heterogeneous edge networks is a fundamental bottleneck in Federated Learning (FL), restricting both model capacity and user participation. To address this issue, we introduce two novel strategies to reduce communication costs: (1) the use of lossy compression on the global model sent server-to-client; and (2) Federated Dropout, which allows users to efficiently train locally on smaller subsets of the global model and also provides a reduction in both client-to-server communication and local computation. We empirically show that these strategies, combined with existing compression approaches for client-to-server communication, collectively provide up to a 14× reduction in server-to-client communication, a 1.7× reduction in local computation, and a 28× reduction in upload communication, all without degrading the quality of the final model. We thus comprehensively reduce FL's impact on client device resources, allowing higher capacity models to be trained, and a more diverse set of users to be reached.
Key facts. Cited by 163 papers in the map (data through 14 Oct 2026). First posted on arXiv 18 Dec 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 38; 2022: 33; 2023: 31; 2024: 29; 2025: 19; 2026: 13.
163 papers.
Sort:
By area:
- 2021Federated Learning on Non-IID Data: A Surveycited by 346
- 2021FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropoutcited by 192
- 2021FedKD: Communication Efficient Federated Learning via Knowledge Distillationcited by 187
- 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 161
- 2021Distributed Learning in Wireless Networks: Recent Progress and Future Challengescited by 129
- 2022FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extractioncited by 102
- 2021From Distributed Machine Learning to Federated Learning: A Surveycited by 66
- 2021Towards Fairness-Aware Federated Learningcited by 58
- 2021EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learningcited by 55
- 2021DRIVE: One-bit Distributed Mean Estimationcited by 52
- 2022ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsitycited by 45
- 2022A Survey on Heterogeneous Federated Learningcited by 42
38 more
- 2023Recent Advances on Federated Learning: A Systematic Surveycited by 41
- 2023Federated Learning for Computationally-Constrained Heterogeneous Devices: A Surveycited by 40
- 2022No One Left Behind: Inclusive Federated Learning over Heterogeneous Devicescited by 37
- 2021FedJAX: Federated learning simulation with JAXcited by 32
- 2022Enable Deep Learning on Mobile Devices: Methods, Systems, and Applicationscited by 32
- 2025Vision-Language Models for Edge Networks: A Comprehensive Surveycited by 29
- 2021Federated Mixture of Expertscited by 28
- 2024Federated LoRA with Sparse Communicationcited by 26
- 2022Scaling Language Model Size in Cross-Device Federated Learningcited by 25
- 2024Decentralized Federated Learning: A Survey on Security and Privacycited by 25
- 2023DFRD: Data-Free Robustness Distillation for Heterogeneous Federated Learningcited by 24
- 2023Every Parameter Matters: Ensuring the Convergence of Federated Learning with Dynamic Heterogeneous Models Reductioncited by 24
- 2022Accelerated Federated Learning with Decoupled Adaptive Optimizationcited by 23
- 2023Privacy Amplification via Compression: Achieving the Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimationcited by 22
- 2022FedShuffle: Recipes for Better Use of Local Work in Federated Learningcited by 21
- 2024FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extractioncited by 21
- 2023MP-FedCL: Multiprototype Federated Contrastive Learning for Edge Intelligencecited by 20
- 2022Towards Fair Federated Recommendation Learning: Characterizing the Inter-Dependence of System and Data Heterogeneitycited by 17
- 2021FedSAE: A Novel Self-Adaptive Federated Learning Framework in Heterogeneous Systemscited by 16
- 2022Distributed Contrastive Learning for Medical Image Segmentationcited by 16
- 2023FLuID: Mitigating Stragglers in Federated Learning using Invariant Dropoutcited by 16
- 2021SGDE: Secure Generative Data Exchange for Cross-Silo Federated Learningcited by 15
- 2022Wireless Quantized Federated Learning: A Joint Computation and Communication Designcited by 15
- 2021Partial Variable Training for Efficient On-Device Federated Learningcited by 14
- 2022Correlated quantization for distributed mean estimation and optimizationcited by 14
- 2022Combined Federated and Split Learning in Edge Computing for Ubiquitous Intelligence in Internet of Things: State of the Art and Future Directionscited by 14
- 2021Efficient and Private Federated Learning with Partially Trainable Networkscited by 13
- 2022Continual Learning for Peer-to-Peer Federated Learning: A Study on Automated Brain Metastasis Identificationcited by 13
- 2022A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairnesscited by 13
- 2021Enabling On-Device Training of Speech Recognition Models with Federated Dropoutcited by 12
- 2021FedPrune: Towards Inclusive Federated Learningcited by 12
- 2022Quantization Robust Federated Learning for Efficient Inference on Heterogeneous Devicescited by 12
- 2023BAFFLE: A Baseline of Backpropagation-Free Federated Learningcited by 12
- 2024Recurrent Early Exits for Federated Learning with Heterogeneous Clientscited by 12
- 2021FedCon: A Contrastive Framework for Federated Semi-Supervised Learningcited by 11
- 2022Federated Select: A Primitive for Communication- and Memory-Efficient Federated Learningcited by 11
- 2021A Payload Optimization Method for Federated Recommender Systemscited by 10
- 2021DISTREAL: Distributed Resource-Aware Learning in Heterogeneous Systemscited by 10
50 most cited of 163 All 163 (JSON)
- 2026Fast Quantized Johnson-Lindenstrauss Transforms12 Oct 2026
- 2026Resource-Aware Federated Mixture-of-Experts with Adaptive Pruning for Onboard Learning in LEO Satellite Constellations25 Sep 2026
- 2026Partially-Observable Transmission Control for UAV-Enabled Federated Learning in IoT Networks1 Aug 2026
- 2026Federated Low-Rank Koopman Learning for Multivariate Time-Series Anomaly Detection in IoT Systems9 Jul 2026
- 2026Collate: Collaborative Neural Network Learning for Latency-Critical Edge Systems9 Jul 2026
- 2026HASA: Subnet Allocation for Compute-Constrained Model-Heterogeneous Federated Learning30 May 2026
- 2026Bandwidth Allocation with Device Partitioning for Federated Learning over Industrial IoT networks29 May 2026
- 2026Quantizing With Randomized Hadamard Transforms: Efficient Heuristic Now Proven7 May 2026
- 2026Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy25 Apr 2026
- 2026Representation-Aligned Multi-Scale Personalization for Federated Learning13 Apr 2026
- 2026SubFLOT: Submodel Extraction for Efficient and Personalized Federated Learning via Optimal Transport8 Apr 2026
- 2026PrivacyBench: Privacy Isn't Free in Hybrid Privacy-Preserving Vision Systems21 Feb 2026
38 more
- 2026Tackling Resource-Constrained and Data-Heterogeneity in Federated Learning with Double-Weight Sparse Pack5 Jan 2026
- 2025Energy and Memory-Efficient Federated Learning With Ordered Layer Freezing29 Dec 2025
- 2025First Provable Guarantees for Practical Private FL: Beyond Restrictive Assumptions25 Dec 2025
- 2025DFedReweighting: A Unified Framework for Objective-Oriented Reweighting in Decentralized Federated Learning12 Dec 2025
- 2025CycleSL: Server-Client Cyclical Update Driven Scalable Split Learning23 Nov 2025
- 2025CLIP: Client-Side Invariant Pruning for Mitigating Stragglers in Secure Federated Learning19 Oct 2025
- 2025FedEL: Federated Elastic Learning for Heterogeneous Devices21 Sep 2025
- 2025Bridging Generalization Gap of Heterogeneous Federated Clients Using Generative Models3 Aug 2025
- 2025Hypernetworks for Model-Heterogeneous Personalized Federated Learning30 Jul 2025
- 2025Model Parallelism With Subnetwork Data Parallelism11 Jul 2025
- 2025The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning29 May 2025
- 2025Mosaic: Data-Free Knowledge Distillation via Mixture-of-Experts for Heterogeneous Distributed Environments26 May 2025
- 2025FedDiverse: Tackling Data Heterogeneity in Federated Learning with Diversity-Driven Client Selection15 Apr 2025
- 2025FedSAUC: A Similarity-Aware Update Control for Communication-Efficient Federated Learning in Edge Computing7 Apr 2025
- 2025Moss: Proxy Model-based Full-Weight Aggregation in Federated Learning with Heterogeneous Models13 Mar 2025
- 2025Efficient Zeroth-Order Federated Finetuning of Language Models on Resource-Constrained Devices14 Feb 2025
- 2025Towards Seamless Hierarchical Federated Learning under Intermittent Client Participation: A Stagewise Decision-Making Methodology13 Feb 2025
- 2025FedMHO: Heterogeneous One-Shot Federated Learning Towards Resource-Constrained Edge Devices12 Feb 2025
- 2025Vision-Language Models for Edge Networks: A Comprehensive Survey11 Feb 2025
- 2025Advancing Personalized Federated Learning: Integrative Approaches with AI for Enhanced Privacy and Customization30 Jan 2025
- 2024The Impact of Cut Layer Selection in Split Federated Learning20 Dec 2024
- 2024Learnable Sparse Customization in Heterogeneous Edge Computing10 Dec 2024
- 2024DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices8 Dec 2024
- 2024Efficient Federated Finetuning of Tiny Transformers with Resource-Constrained Devices12 Nov 2024
- 2024Photon: Federated LLM Pre-Training5 Nov 2024
- 2024On Sampling Strategies for Spectral Model Sharding31 Oct 2024
- 2024Why Go Full? Elevating Federated Learning Through Partial Network Updates15 Oct 2024
- 2024Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge Integration27 Sep 2024
- 2024Communication-Efficient Federated Low-Rank Update Algorithm and its Connection to Implicit Regularization19 Sep 2024
- 2024FedProphet: Memory-Efficient Federated Adversarial Training via Robust and Consistent Cascade Learning12 Sep 2024
- 2024FedFT: Improving Communication Performance for Federated Learning with Frequency Space Transformation8 Sep 2024
- 2024FedBAT: Communication-Efficient Federated Learning via Learnable Binarization6 Aug 2024
- 2024FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction28 Jul 2024
- 2024Federated Learning with a Single Shared Image18 Jun 2024
- 2024Federated LoRA with Sparse Communication7 Jun 2024
- 2024Sparse-ProxSkip: Accelerated Sparse-to-Sparse Training in Federated Learning31 May 2024
- 2024SPAM: Stochastic Proximal Point Method with Momentum Variance Reduction for Non-convex Cross-Device Federated Learning30 May 2024
- 2024subMFL: Compatiple subModel Generation for Federated Learning in Device Heterogenous Environment30 May 2024
50 newest of 163 All 163 (JSON)
- 2021Federated Learning on Non-IID Data: A Surveycited by 346
- 2021FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropoutcited by 192
- 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 161
- 2021Distributed Learning in Wireless Networks: Recent Progress and Future Challengescited by 129
- 2022FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extractioncited by 102
- 2021From Distributed Machine Learning to Federated Learning: A Surveycited by 66
- 2021Towards Fairness-Aware Federated Learningcited by 58
- 2021EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learningcited by 55
- 2021DRIVE: One-bit Distributed Mean Estimationcited by 52
- 2022ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsitycited by 45
- 2022A Survey on Heterogeneous Federated Learningcited by 42
- 2023Recent Advances on Federated Learning: A Systematic Surveycited by 41
12 most cited of 156 All 156 (JSON)
- 2026Fast Quantized Johnson-Lindenstrauss Transforms12 Oct 2026
- 2026Partially-Observable Transmission Control for UAV-Enabled Federated Learning in IoT Networks1 Aug 2026
- 2026Federated Low-Rank Koopman Learning for Multivariate Time-Series Anomaly Detection in IoT Systems9 Jul 2026
- 2026Collate: Collaborative Neural Network Learning for Latency-Critical Edge Systems9 Jul 2026
- 2026HASA: Subnet Allocation for Compute-Constrained Model-Heterogeneous Federated Learning30 May 2026
- 2026Bandwidth Allocation with Device Partitioning for Federated Learning over Industrial IoT networks29 May 2026
- 2026Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy25 Apr 2026
- 2026Representation-Aligned Multi-Scale Personalization for Federated Learning13 Apr 2026
- 2026SubFLOT: Submodel Extraction for Efficient and Personalized Federated Learning via Optimal Transport8 Apr 2026
- 2026PrivacyBench: Privacy Isn't Free in Hybrid Privacy-Preserving Vision Systems21 Feb 2026
- 2026Tackling Resource-Constrained and Data-Heterogeneity in Federated Learning with Double-Weight Sparse Pack5 Jan 2026
- 2025Energy and Memory-Efficient Federated Learning With Ordered Layer Freezing29 Dec 2025
12 newest of 156 All 156 (JSON)