Energy and Memory-Efficient Federated Learning With Ordered Layer Freezing

• URL: http://arxiv.org/abs/2512.23200v1
• Date: Mon, 29 Dec 2025 04:39:33 GMT
• Title: Energy and Memory-Efficient Federated Learning With Ordered Layer Freezing
• Authors: Ziru Niu, Hai Dong, A. K. Qin, Tao Gu, Pengcheng Zhang,
• Abstract summary: 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)<n>We introduce Federated Learning with Ordered Layer Freezing (FedOLF)<n>FedOLF consistently freezes layers in a predefined order before training, significantly mitigating communication and memory requirements.
• Score: 8.403142088918843
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: 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.

Related papers

• SHeRL-FL: When Representation Learning Meets Split Learning in Hierarchical Federated Learning [5.447833971100033]
  Federated learning (FL) is a promising approach for addressing scalability and latency issues in large-scale networks.<n>Previous works combine split learning (SL) and hierarchical FL (HierFL) to reduce device-side computation, but this introduces training complexity due to coordination across tiers.<n>We propose SHeRL-FL, which integrates SL and hierarchical model aggregation and incorporates representation learning at intermediate layers.
  arXiv  Detail & Related papers  (2025-08-11T04:13:56Z)
• Caching Techniques for Reducing the Communication Cost of Federated Learning in IoT Environments [2.942616054218564]
  Federated Learning (FL) allows multiple devices to jointly train a shared model without centralizing data.<n>This paper introduces caching strategies - FIFO, LRU, and Priority-Based - to reduce unnecessary model update transmissions.
  arXiv  Detail & Related papers  (2025-07-19T17:02:15Z)
• Lightweight Federated Learning over Wireless Edge Networks [83.4818741890634]
  Federated (FL) is an alternative at network edge, but an alternative in wireless networks.<n>We derive a closed-form expression FL convergence gap transmission power, model pruning error, and quantization.<n> LTFL outperforms state-the-art schemes in experiments on real-world datasets.
  arXiv  Detail & Related papers  (2025-07-13T09:14:17Z)
• Efficient Federated Fine-Tuning of Large Language Models with Layer Dropout [15.009864792277236]
  Fine-tuning plays a crucial role in enabling pre-trained LLMs to evolve from general language comprehension to task-specific expertise.<n>This work proposes DropPEFT, an innovative federated PEFT framework that employs a novel transformer dropout method.<n>We show that DropPEFT can achieve a 1.3-6.3times speedup in model convergence and a 40%-67% reduction in memory footprint.
  arXiv  Detail & Related papers  (2025-03-13T09:59:16Z)
• Federated Learning with Workload Reduction through Partial Training of Client Models and Entropy-Based Data Selection [3.9981390090442694]
  We propose FedFT-EDS, a novel approach that combines Fine-Tuning of partial client models with Entropy-based Data Selection to reduce training workloads on edge devices.<n>Our experiments show that FedFT-EDS uses only 50% user data while improving the global model performance compared to baseline methods, FedAvg and FedProx.<n>FedFT-EDS improves client learning efficiency by up to 3 times, using one third of training time on clients to achieve an equivalent performance to the baselines.
  arXiv  Detail & Related papers  (2024-12-30T22:47:32Z)
• Adaptive Model Pruning and Personalization for Federated Learning over Wireless Networks [72.59891661768177]
  Federated learning (FL) enables distributed learning across edge devices while protecting data privacy. We consider a FL framework with partial model pruning and personalization to overcome these challenges. This framework splits the learning model into a global part with model pruning shared with all devices to learn data representations and a personalized part to be fine-tuned for a specific device.
  arXiv  Detail & Related papers  (2023-09-04T21:10:45Z)
• Adaptive Federated Pruning in Hierarchical Wireless Networks [69.6417645730093]
  Federated Learning (FL) is a privacy-preserving distributed learning framework where a server aggregates models updated by multiple devices without accessing their private datasets. In this paper, we introduce model pruning for HFL in wireless networks to reduce the neural network scale. We show that our proposed HFL with model pruning achieves similar learning accuracy compared with the HFL without model pruning and reduces about 50 percent communication cost.
  arXiv  Detail & Related papers  (2023-05-15T22:04:49Z)
• CoCoFL: Communication- and Computation-Aware Federated Learning via Partial NN Freezing and Quantization [3.219812767529503]
  We present a novel FL technique, CoCoFL, which maintains the full NN structure on all devices. CoCoFL efficiently utilizes the available resources on devices and allows constrained devices to make a significant contribution to the FL system.
  arXiv  Detail & Related papers  (2022-03-10T16:45:05Z)
• Exploring Deep Reinforcement Learning-Assisted Federated Learning for Online Resource Allocation in EdgeIoT [53.68792408315411]
  Federated learning (FL) has been increasingly considered to preserve data training privacy from eavesdropping attacks in mobile edge computing-based Internet of Thing (EdgeIoT) We propose a new federated learning-enabled twin-delayed deep deterministic policy gradient (FLDLT3) framework to achieve the optimal accuracy and energy balance in a continuous domain. Numerical results demonstrate that the proposed FL-DLT3 achieves fast convergence (less than 100 iterations) while the FL accuracy-to-energy consumption ratio is improved by 51.8% compared to existing state-of-the-art benchmark.
  arXiv  Detail & Related papers  (2022-02-15T13:36:15Z)
• Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Better [88.28293442298015]
  Federated learning (FL) enables distribution of machine learning workloads from the cloud to resource-limited edge devices. We develop, implement, and experimentally validate a novel FL framework termed Federated Dynamic Sparse Training (FedDST) FedDST is a dynamic process that extracts and trains sparse sub-networks from the target full network.
  arXiv  Detail & Related papers  (2021-12-18T02:26:38Z)
• On the Tradeoff between Energy, Precision, and Accuracy in Federated Quantized Neural Networks [68.52621234990728]
  Federated learning (FL) over wireless networks requires balancing between accuracy, energy efficiency, and precision. We propose a quantized FL framework that represents data with a finite level of precision in both local training and uplink transmission. Our framework can reduce energy consumption by up to 53% compared to a standard FL model.
  arXiv  Detail & Related papers  (2021-11-15T17:00:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.