mlsanityData to 14 Oct 2026

FedEL: Federated Elastic Learning for Heterogeneous Devices

arXiv 2509.16902 ↗First posted 21 Sep 2025cs.LG cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) enables distributed devices to collaboratively train machine learning models while maintaining data privacy. However, the heterogeneous hardware capabilities of devices often result in significant training delays, as straggler clients with limited resources prolong the aggregation process. Existing solutions such as client selection, asynchronous FL, and partial training partially address these challenges but encounter issues such as reduced accuracy, stale updates, and compromised model performance due to inconsistent training contributions. To overcome these limitations, we propose FedEL, a federated elastic learning framework that enhances training efficiency while maintaining model accuracy. FedEL introduces a novel window-based training process, sliding the window to locate the training part of the model and dynamically selecting important tensors for training within a coordinated runtime budget. This approach ensures progressive and balanced training across all clients, including stragglers. Additionally, FedEL employs a tensor importance adjustment module, harmonizing local and global tensor importance to mitigate biases caused by data heterogeneity. The experiment results show that FedEL achieves up to 3.87x improvement in time-to-accuracy compared to baselines while maintaining or exceeding final test accuracy.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 36 of its 58 references that are in the map. First posted on arXiv 21 Sep 2025.

Builds on

36 of 58 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  4. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  5. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,790
  6. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  7. 2018Federated Learning with Non-IID Datacited by 1,108
  8. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
  9. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 752
  10. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 352
  11. 2020HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clientscited by 337
  12. 2019Model Pruning Enables Efficient Federated Learning on Edge Devicescited by 222
24 more
  1. 2021FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropoutcited by 192
  2. 2018Expanding the Reach of Federated Learning by Reducing Client Resource Requirementscited by 163
  3. 2022On-Device Training Under 256KB Memorycited by 160
  4. 2021FedScale: Benchmarking Model and System Performance of Federated Learning at Scalecited by 136
  5. 2022FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extractioncited by 102
  6. 2021Asynchronous Federated Learning on Heterogeneous Devices: A Surveycited by 93
  7. 2023FedDisco: Federated Learning with Discrepancy-Aware Collaborationcited by 67
  8. 2022FedCorr: Multi-Stage Federated Learning for Label Noise Correctioncited by 61
  9. 2017meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfittingcited by 34
  10. 2022Mandheling: Mixed-Precision On-Device DNN Training with DSP Offloadingcited by 29
  11. 2024Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domainscited by 28
  12. 2022FedFM: Anchor-based Feature Matching for Data Heterogeneity in Federated Learningcited by 27
  13. 2023TimelyFL: Heterogeneity-aware Asynchronous Federated Learning with Adaptive Partial Trainingcited by 27
  14. 2022POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Pagingcited by 26
  15. 2023Every Parameter Matters: Ensuring the Convergence of Federated Learning with Dynamic Heterogeneous Models Reductioncited by 24
  16. 2024FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extractioncited by 21
  17. 2022On-device Training: A First Overview on Existing Systemscited by 19
  18. 2023Accelerating Hybrid Federated Learning Convergence under Partial Participationcited by 15
  19. 2023AEDFL: Efficient Asynchronous Decentralized Federated Learning with Heterogeneous Devicescited by 15
  20. 2021Elbert: Fast Albert with Confidence-Window Based Early Exitcited by 14
  21. 2023ElasticTrainer: Speeding Up On-Device Training with Runtime Elastic Tensor Selectioncited by 12
  22. 2024Recurrent Early Exits for Federated Learning with Heterogeneous Clientscited by 12
  23. 2024Heterogeneity-Aware Memory Efficient Federated Learning via Progressive Layer Freezingcited by 10
  24. 2023Federated Learning with Instance-Dependent Noisy Labelcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026FedTreeLoRA: Reconciling Statistical and Functional Heterogeneity in Federated LoRA Fine-Tuningcited by 2
  2. 2026Fractional Order Federated Learning for Battery Electric Vehicle Energy Consumption Modelingcited by 0
  3. 2026FEAST: Federated Shared-Space Training for Resource-Heterogeneous Clientscited by 0