mlsanityData to 14 Oct 2026

Energy and Memory-Efficient Federated Learning With Ordered Layer Freezing

arXiv 2512.23200 ↗First posted 29 Dec 2025cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) has emerged as a privacy-preserving paradigm for training machine learning models across distributed edge devices in the Internet of Things (IoT). By keeping data local and coordinating model training through a central server, FL effectively addresses privacy concerns and reduces communication overhead. However, the limited computational power, memory, and bandwidth of IoT edge devices pose significant challenges to the efficiency and scalability of FL, especially when training deep neural networks. Various FL frameworks have been proposed to reduce computation and communication overheads through dropout or layer freezing. However, these approaches often sacrifice accuracy or neglect memory constraints. To this end, in this work, we introduce Federated Learning with Ordered Layer Freezing (FedOLF). FedOLF consistently freezes layers in a predefined order before training, significantly mitigating computation and memory requirements. To further reduce communication and energy costs, we incorporate Tensor Operation Approximation (TOA), a lightweight alternative to conventional quantization that better preserves model accuracy. Experimental results demonstrate that over non-iid data, FedOLF achieves at least 0.3%, 6.4%, 5.81%, 4.4%, 6.27% and 1.29% higher accuracy than existing works respectively on EMNIST (with CNN), CIFAR-10 (with AlexNet), CIFAR-100 (with ResNet20 and ResNet44), and CINIC-10 (with ResNet20 and ResNet44), along with higher energy efficiency and lower memory footprint.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 30 of its 61 references that are in the map. First posted on arXiv 29 Dec 2025.

Builds on

30 of 61 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  4. 2019Similarity of Neural Network Representations Revisitedcited by 1,755
  5. 2021Federated Learning Based on Dynamic Regularizationcited by 562
  6. 2020Flower: A Friendly Federated Learning Research Frameworkcited by 455
  7. 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 419
  8. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 352
  9. 2020HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clientscited by 337
  10. 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
  11. 2019Model Pruning Enables Efficient Federated Learning on Edge Devicescited by 222
  12. 2017EMNIST: an extension of MNIST to handwritten letterscited by 213
18 more
  1. 2021FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropoutcited by 192
  2. 2021Federated Learning for Smart Healthcare: A Surveycited by 184
  3. 2020FetchSGD: Communication-Efficient Federated Learning with Sketchingcited by 179
  4. 2018Expanding the Reach of Federated Learning by Reducing Client Resource Requirementscited by 163
  5. 2020Federated Learning with Compression: Unified Analysis and Sharp Guaranteescited by 160
  6. 2020Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Datacited by 125
  7. 2023AutoFed: Heterogeneity-Aware Federated Multimodal Learning for Robust Autonomous Drivingcited by 32
  8. 2022FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated Learningcited by 23
  9. 2024FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extractioncited by 21
  10. 2022FedOBD: Opportunistic Block Dropout for Efficiently Training Large-scale Neural Networks through Federated Learningcited by 17
  11. 2018Faster Neural Network Training with Approximate Tensor Operationscited by 14
  12. 2021Efficient and Private Federated Learning with Partially Trainable Networkscited by 13
  13. 2023FLrce: Resource-Efficient Federated Learning with Early-Stopping Strategycited by 10
  14. 2024Heterogeneity-Aware Memory Efficient Federated Learning via Progressive Layer Freezingcited by 10
  15. 2023AdaptiveFL: Adaptive Heterogeneous Federated Learning for Resource-Constrained AIoT Systemscited by 9
  16. 2022CoCoFL: Communication- and Computation-Aware Federated Learning via Partial NN Freezing and Quantizationcited by 7
  17. 2023Aggregating Capacity in FL through Successive Layer Training for Computationally-Constrained Devicescited by 7
  18. 2023NeFL: Nested Model Scaling for Federated Learning with System Heterogeneous Clientscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Entropy-Guided Tensor Compression for Multimodal Federated Learning on Edge Devicescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025FedBiF: Communication-Efficient Federated Learning via Bits Freezing
  2. 2023REFT: Resource-Efficient Federated Training Framework for Heterogeneous and Resource-Constrained Environments
  3. 2021FEDZIP: A Compression Framework for Communication-Efficient Federated Learning
  4. 2026CoCo-Fed: A Unified Framework for Memory- and Communication-Efficient Federated Learning at the Wireless Edge
  5. 2024Communication and Energy Efficient Federated Learning using Zero-Order Optimization Technique
  6. 2026Reliable Federated TinyML Deployment for IoT Security
  7. 2025Energy-Efficient Federated Learning for Edge Real-Time Vision via Joint Data, Computation, and Communication Design
  8. 2021Communication-Efficient Federated Learning with Binary Neural Networks