Model Pruning Enables Efficient Federated Learning on Edge Devices
Not on the map. Why?
Abstract (arXiv)
Federated learning (FL) allows model training from local data collected by edge/mobile devices while preserving data privacy, which has wide applicability to image and vision applications. A challenge is that client devices in FL usually have much more limited computation and communication resources compared to servers in a datacenter. To overcome this challenge, we propose PruneFL -- a novel FL approach with adaptive and distributed parameter pruning, which adapts the model size during FL to reduce both communication and computation overhead and minimize the overall training time, while maintaining a similar accuracy as the original model. PruneFL includes initial pruning at a selected client and further pruning as part of the FL process. The model size is adapted during this process, which includes maximizing the approximate empirical risk reduction divided by the time of one FL round. Our experiments with various datasets on edge devices (e.g., Raspberry Pi) show that: (i) we significantly reduce the training time compared to conventional FL and various other pruning-based methods; (ii) the pruned model with automatically determined size converges to an accuracy that is very similar to the original model, and it is also a lottery ticket of the original model.
Key facts. Cited by 219 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Sep 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 18; 2022: 32; 2023: 52; 2024: 64; 2025: 38; 2026: 15.
219 papers.
Sort:
By area:
- 2023A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendationscited by 200
- 2021FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropoutcited by 192
- 2023Structured Pruning for Deep Convolutional Neural Networks: A surveycited by 122
- 2021What Do We Mean by Generalization in Federated Learning?cited by 62
- 2021Towards Fairness-Aware Federated Learningcited by 57
- 2021FedLab: A Flexible Federated Learning Frameworkcited by 54
- 2021Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Bettercited by 54
- 2023Federated Foundation Models: Privacy-Preserving and Collaborative Learning for Large Modelscited by 49
- 2022ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsitycited by 45
- 2021DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learningcited by 40
- 2023Federated Learning for Computationally-Constrained Heterogeneous Devices: A Surveycited by 40
- 2023Efficient Personalized Federated Learning via Sparse Model-Adaptationcited by 38
38 more
- 2023pFedLoRA: Model-Heterogeneous Personalized Federated Learning with LoRA Tuningcited by 38
- 2021Layer-wise Adaptive Model Aggregation for Scalable Federated Learningcited by 35
- 2024Advances and Open Challenges in Federated Foundation Modelscited by 33
- 2022Sparse Random Networks for Communication-Efficient Federated Learningcited by 32
- 2022FedDUAP: Federated Learning with Dynamic Update and Adaptive Pruning Using Shared Data on the Servercited by 29
- 2023Why Batch Normalization Damage Federated Learning on Non-IID Data?cited by 29
- 2024A Survey on Efficient Federated Learning Methods for Foundation Model Trainingcited by 29
- 2022Machine Learning for Microcontroller-Class Hardware: A Reviewcited by 28
- 2021Cost-Effective Federated Learning in Mobile Edge Networkscited by 25
- 2024Decentralized Federated Learning: A Survey on Security and Privacycited by 25
- 2023Every Parameter Matters: Ensuring the Convergence of Federated Learning with Dynamic Heterogeneous Models Reductioncited by 24
- 2023Green Edge AI: A Contemporary Surveycited by 24
- 2024Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Modelscited by 23
- 2024FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extractioncited by 21
- 2021UAV-assisted Online Machine Learning over Multi-Tiered Networks: A Hierarchical Nested Personalized Federated Learning Approachcited by 20
- 2025Ten Challenging Problems in Federated Foundation Modelscited by 20
- 2023Communication-Efficient Split Learning via Adaptive Feature-Wise Compressioncited by 18
- 2021Architectural Patterns for the Design of Federated Learning Systemscited by 17
- 2023FedICT: Federated Multi-task Distillation for Multi-access Edge Computingcited by 17
- 2023HiFlash: Communication-Efficient Hierarchical Federated Learning with Adaptive Staleness Control and Heterogeneity-aware Client-Edge Associationcited by 17
- 2022Distributed Contrastive Learning for Medical Image Segmentationcited by 16
- 2023FLuID: Mitigating Stragglers in Federated Learning using Invariant Dropoutcited by 16
- 2023Accelerating Split Federated Learning over Wireless Communication Networkscited by 16
- 2024Distributed Deep Reinforcement Learning Based Gradient Quantization for Federated Learning Enabled Vehicle Edge Computingcited by 15
- 2024FedMef: Towards Memory-efficient Federated Dynamic Pruningcited by 14
- 2024Synergizing Foundation Models and Federated Learning: A Surveycited by 14
- 2024Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challengescited by 14
- 2025Can Textual Gradient Work in Federated Learning?cited by 14
- 2024Rethinking Resource Management in Edge Learning: A Joint Pre-training and Fine-tuning Design Paradigmcited by 13
- 2024FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneitycited by 13
- 2024Asteroid: Resource-Efficient Hybrid Pipeline Parallelism for Collaborative DNN Training on Heterogeneous Edge Devicescited by 13
- 2021FedPrune: Towards Inclusive Federated Learningcited by 12
- 2022HCFL: A High Compression Approach for Communication-Efficient Federated Learning in Very Large Scale IoT Networkscited by 12
- 2022Quantization Robust Federated Learning for Efficient Inference on Heterogeneous Devicescited by 12
- 2022Lottery Aware Sparsity Hunting: Enabling Federated Learning on Resource-Limited Edgecited by 12
- 2023Complement Sparsification: Low-Overhead Model Pruning for Federated Learningcited by 12
- 2023ElasticTrainer: Speeding Up On-Device Training with Runtime Elastic Tensor Selectioncited by 12
- 2022Distributed Pruning Towards Tiny Neural Networks in Federated Learningcited by 11
50 most cited of 219 All 219 (JSON)
- 2026FedSAP: Federated Learning with Structured Adaptive Partitioning for Multi-Domain Heterogeneous Edge Devices1 Oct 2026
- 2026Rethinking the Transferable Adversarial Attacks and Robust Defense in Federated Learning25 Aug 2026
- 2026Capacity Confounds and Coverage Guarantees in Adaptive Sub-model Federated Learning7 Aug 2026
- 2026FedASAP: Activation Statistics-driven Structured Adaptive Pruning for Efficient Personalized Federated Learning for Lesion Segmentation on brain MRI20 Jul 2026
- 2026Range Penalization: Theoretical Insights with Applications in Federated Learning9 Jun 2026
- 2026Fed-DLoRA: Efficient Wireless Federated Learning with Dynamic Low-Rank Adaptation27 Apr 2026
- 2026Semantic-based Distributed Learning for Diverse and Discriminative Representations20 Apr 2026
- 2026Representation-Aligned Multi-Scale Personalization for Federated Learning13 Apr 2026
- 2026Joint Routing and Model Pruning for Decentralized Federated Learning in Bandwidth-Constrained Multi-Hop Wireless Networks16 Mar 2026
- 2026SCOPE: Semantic Coreset with Orthogonal Projection Embeddings for Federated learning13 Mar 2026
- 2026CA-HFP: Curvature-Aware Heterogeneous Federated Pruning with Model Reconstruction13 Mar 2026
- 2026EdgeFLow: Serverless Federated Learning via Sequential Model Migration in Edge Networks3 Mar 2026
38 more
- 2026ERIS: Enhancing Privacy and Scalability in Federated Learning via Federated Shard Aggregation9 Feb 2026
- 2026Communication-Efficient Federated Learning by Exploiting Spatio-Temporal Correlations of Gradients15 Jan 2026
- 2026QFed: Parameter-Compact Quantum-Classical Federated Learning14 Jan 2026
- 2025Energy and Memory-Efficient Federated Learning With Ordered Layer Freezing29 Dec 2025
- 2025Parallax: Runtime Parallelization for Operator Fallbacks in Heterogeneous Edge Systems12 Dec 2025
- 2025Skewness-Guided Pruning of Multimodal Swin Transformers for Federated Skin Lesion Classification on Edge Devices9 Dec 2025
- 2025ParaBlock: Communication-Computation Parallel Block Coordinate Federated Learning for Large Language Models25 Nov 2025
- 2025On the Convergence and Stability of Distributed Sub-model Training8 Nov 2025
- 2025TT-Prune: Joint Model Pruning and Resource Allocation for Communication-efficient Time-triggered Federated Learning6 Nov 2025
- 2025CLIP: Client-Side Invariant Pruning for Mitigating Stragglers in Secure Federated Learning19 Oct 2025
- 2025RockNet: Distributed Learning on Ultra-Low-Power Devices15 Oct 2025
- 2025FedEL: Federated Elastic Learning for Heterogeneous Devices21 Sep 2025
- 2025FedBiF: Communication-Efficient Federated Learning via Bits Freezing12 Sep 2025
- 2025Foundational Models and Federated Learning: Survey, Taxonomy, Challenges and Practical Insights5 Sep 2025
- 2025FedKLPR: KL-Guided Pruning-Aware Federated Learning for Person Re-Identification24 Aug 2025
- 2025FedX: Explanation-Guided Pruning for Communication-Efficient Federated Learning in Remote Sensing8 Aug 2025
- 2025Energy-Efficient Federated Learning for Edge Real-Time Vision via Joint Data, Computation, and Communication Design3 Aug 2025
- 2025Bridging Generalization Gap of Heterogeneous Federated Clients Using Generative Models3 Aug 2025
- 2025Resource-Efficient Automatic Software Vulnerability Assessment via Knowledge Distillation and Particle Swarm Optimization30 Jul 2025
- 2025Optimal Batch-Size Control for Low-Latency Federated Learning with Device Heterogeneity21 Jul 2025
- 2025Efficient Federated Learning with Heterogeneous Data and Adaptive Dropout14 Jul 2025
- 2025TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments6 Jul 2025
- 2025DOME: Improving Signal-to-Noise in Stochastic Gradient Descent via Sharp-Direction Subspace Filtering4 Jul 2025
- 2025Efficient Federated Learning with Encrypted Data Sharing for Data-Heterogeneous Edge Devices25 Jun 2025
- 2025Computation- and Communication-Efficient Online FL for Resource-Constrained Aerial Vehicles3 Jun 2025
- 2025Addressing the Collaboration Dilemma in Low-Data Federated Learning via Transient Sparsity1 Jun 2025
- 2025SEMFED: Semantic-Aware Resource-Efficient Federated Learning for Heterogeneous NLP Tasks26 May 2025
- 2025Onboard Optimization and Learning: A Survey7 May 2025
- 2025Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity24 Apr 2025
- 2025Collaborative Split Federated Learning with Parallel Training and Aggregation22 Apr 2025
- 2025Embedded Federated Feature Selection with Dynamic Sparse Training: Balancing Accuracy-Cost Tradeoffs7 Apr 2025
- 2025Leveraging Label Potential for Enhanced Multimodal Emotion Recognition7 Apr 2025
- 2025Layer-wise Update Aggregation with Recycling for Communication-Efficient Federated Learning14 Mar 2025
- 2025Efficient Federated Fine-Tuning of Large Language Models with Layer Dropout13 Mar 2025
- 2025Drift-Aware Federated Learning: A Causal Perspective12 Mar 2025
- 2025FedOptima: Optimizing Resource Utilization in Federated Learning10 Mar 2025
- 2025Can Textual Gradient Work in Federated Learning?27 Feb 2025
- 2025Signal Collapse in One-Shot Pruning: When Sparse Models Fail to Distinguish Neural Representations18 Feb 2025
50 newest of 219 All 219 (JSON)
- 2023A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendationscited by 200
- 2021FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropoutcited by 192
- 2023Structured Pruning for Deep Convolutional Neural Networks: A surveycited by 122
- 2021What Do We Mean by Generalization in Federated Learning?cited by 62
- 2021Towards Fairness-Aware Federated Learningcited by 57
- 2021FedLab: A Flexible Federated Learning Frameworkcited by 54
- 2021Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Bettercited by 54
- 2023Federated Foundation Models: Privacy-Preserving and Collaborative Learning for Large Modelscited by 49
- 2022ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsitycited by 45
- 2021DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learningcited by 40
- 2023Federated Learning for Computationally-Constrained Heterogeneous Devices: A Surveycited by 40
- 2023Efficient Personalized Federated Learning via Sparse Model-Adaptationcited by 38
12 most cited of 215 All 215 (JSON)
- 2026FedSAP: Federated Learning with Structured Adaptive Partitioning for Multi-Domain Heterogeneous Edge Devices1 Oct 2026
- 2026Rethinking the Transferable Adversarial Attacks and Robust Defense in Federated Learning25 Aug 2026
- 2026Capacity Confounds and Coverage Guarantees in Adaptive Sub-model Federated Learning7 Aug 2026
- 2026FedASAP: Activation Statistics-driven Structured Adaptive Pruning for Efficient Personalized Federated Learning for Lesion Segmentation on brain MRI20 Jul 2026
- 2026Range Penalization: Theoretical Insights with Applications in Federated Learning9 Jun 2026
- 2026Fed-DLoRA: Efficient Wireless Federated Learning with Dynamic Low-Rank Adaptation27 Apr 2026
- 2026Semantic-based Distributed Learning for Diverse and Discriminative Representations20 Apr 2026
- 2026Representation-Aligned Multi-Scale Personalization for Federated Learning13 Apr 2026
- 2026Joint Routing and Model Pruning for Decentralized Federated Learning in Bandwidth-Constrained Multi-Hop Wireless Networks16 Mar 2026
- 2026SCOPE: Semantic Coreset with Orthogonal Projection Embeddings for Federated learning13 Mar 2026
- 2026CA-HFP: Curvature-Aware Heterogeneous Federated Pruning with Model Reconstruction13 Mar 2026
- 2026EdgeFLow: Serverless Federated Learning via Sequential Model Migration in Edge Networks3 Mar 2026
12 newest of 215 All 215 (JSON)