QuantFL: Sustainable Federated Learning for Edge IoT via Pre-Trained Model Quantisation
Not on the map. Why?
Abstract (arXiv)
Federated Learning (FL) enables privacy-preserving intelligence on Internet of Things (IoT) devices but incurs a significant carbon footprint due to the high energy cost of frequent uplink transmission. While pre-trained models are increasingly available on edge devices, their potential to reduce the energy overhead of fine-tuning remains underexplored. In this work, we propose QuantFL, a sustainable FL framework that leverages pre-trained initialisation to enable aggressive, computationally lightweight quantisation. We demonstrate that pre-training naturally concentrates update statistics, allowing us to use memory-efficient bucket quantisation without the energy-intensive overhead of complex error-feedback mechanisms. On MNIST and CIFAR-100, QuantFL reduces total communication by 40% (simeq40% total-bit reduction with full-precision downlink; ≥80% on uplink or when downlink is quantised) while matching or exceeding uncompressed baselines under strict bandwidth budgets; BU attains 89.00% (MNIST) and 66.89% (CIFAR-100) test accuracy with orders of magnitude fewer bits. We also account for uplink and downlink costs and provide ablations on quantisation levels and initialisation. QuantFL delivers a practical, "green" recipe for scalable training on battery-constrained IoT networks.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 21 references that are in the map. First posted on arXiv 18 Mar 2026.
Builds on
13 of 21 references.
References · 13
- 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
- 2020Adaptive Federated Optimizationcited by 1,046
- 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
- 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 356
- 2019PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimizationcited by 238
- 2021PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantizationcited by 179
- 2020Federated Learning with Compression: Unified Analysis and Sharp Guaranteescited by 160
- 2022Federated Learning from Pre-Trained Models: A Contrastive Learning Approachcited by 142
- 2017Adaptive Quantization for Deep Neural Networkcited by 67
- 2024SpaFL: Communication-Efficient Federated Learning with Sparse Models and Low computational Overheadcited by 9
- 2025AugFL: Augmenting Federated Learning with Pretrained Modelscited by 6
- 2024Communication-Efficient Federated Learning via Clipped Uniform Quantizationcited by 2
Built on by
Not cited yet.