mlsanityData to 14 Oct 2026

FedSPU: Personalized Federated Learning for Resource-constrained Devices with Stochastic Parameter Update

arXiv 2403.11464 ↗First posted 18 Mar 2024cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Personalized Federated Learning (PFL) is widely employed in IoT applications to handle high-volume, non-iid client data while ensuring data privacy. However, heterogeneous edge devices owned by clients may impose varying degrees of resource constraints, causing computation and communication bottlenecks for PFL. Federated Dropout has emerged as a popular strategy to address this challenge, wherein only a subset of the global model, i.e. a sub-model, is trained on a client's device, thereby reducing computation and communication overheads. Nevertheless, the dropout-based model-pruning strategy may introduce bias, particularly towards non-iid local data. When biased sub-models absorb highly divergent parameters from other clients, performance degradation becomes inevitable. In response, we propose federated learning with stochastic parameter update (FedSPU). Unlike dropout that tailors the global model to small-size local sub-models, FedSPU maintains the full model architecture on each device but randomly freezes a certain percentage of neurons in the local model during training while updating the remaining neurons. This approach ensures that a portion of the local model remains personalized, thereby enhancing the model's robustness against biased parameters from other clients. Experimental results demonstrate that FedSPU outperforms federated dropout by 7.57% on average in terms of accuracy. Furthermore, an introduced early stopping scheme leads to a significant reduction of the training time by 24.8%-70.4% while maintaining high accuracy.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 28 of its 51 references that are in the map. First posted on arXiv 18 Mar 2024.

Builds on

28 of 51 references.

References · 28

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  3. 2019Towards Federated Learning at Scale: System Designcited by 832
  4. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 752
  5. 2017Federated Multi-Task Learningcited by 672
  6. 2020Personalized Federated Learning with Moreau Envelopescited by 618
  7. 2021Federated Learning Based on Dynamic Regularizationcited by 562
  8. 2019Federated Learning with Personalization Layerscited by 541
  9. 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 503
  10. 2020Flower: A Friendly Federated Learning Research Frameworkcited by 455
  11. 2020Adaptive Personalized Federated Learningcited by 358
  12. 2020Three Approaches for Personalization with Applications to Federated Learningcited by 325
16 more
  1. 2020Personalized Federated Learning: A Meta-Learning Approachcited by 312
  2. 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
  3. 2019Model Pruning Enables Efficient Federated Learning on Edge Devicescited by 222
  4. 2017EMNIST: an extension of MNIST to handwritten letterscited by 213
  5. 2020Personalized Federated Learning with First Order Model Optimizationcited by 201
  6. 2021FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropoutcited by 192
  7. 2021Federated Multi-Task Learning under a Mixture of Distributionscited by 192
  8. 2019Adaptive Gradient-Based Meta-Learning Methodscited by 183
  9. 2018Expanding the Reach of Federated Learning by Reducing Client Resource Requirementscited by 163
  10. 2020Survey of Personalization Techniques for Federated Learningcited by 145
  11. 2022FedALA: Adaptive Local Aggregation for Personalized Federated Learningcited by 122
  12. 2018Federated Learning for Keyword Spottingcited by 95
  13. 2014Convolutional Neural Networks at Constrained Time Costcited by 81
  14. 2021Fairness in Cardiac MR Image Analysis: An Investigation of Bias Due to Data Imbalance in Deep Learning Based Segmentationcited by 57
  15. 2023FLrce: Resource-Efficient Federated Learning with Early-Stopping Strategycited by 10
  16. 2023Aggregating Capacity in FL through Successive Layer Training for Computationally-Constrained Devicescited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Tackling Resource-Constrained and Data-Heterogeneity in Federated Learning with Double-Weight Sparse Packcited by 2
  2. 2026Federated Hyperdimensional Computing for Resource-Constrained Industrial IoTcited by 0
  3. 2026FedSAP: Federated Learning with Structured Adaptive Partitioning for Multi-Domain Heterogeneous Edge Devicescited by 0