QuantFL: Sustainable Federated Learning for Edge IoT via Pre-Trained Model Quantisation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917351421640704 |
|---|---|
| author | Herath, Charuka Rahulamathavan, Yogachandran De Silva, Varuna Lambotharan, Sangarapillai |
| author_facet | Herath, Charuka Rahulamathavan, Yogachandran De Silva, Varuna Lambotharan, Sangarapillai |
| contents | 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; $\geq80\%$ 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_17507 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | QuantFL: Sustainable Federated Learning for Edge IoT via Pre-Trained Model Quantisation Herath, Charuka Rahulamathavan, Yogachandran De Silva, Varuna Lambotharan, Sangarapillai Machine Learning Artificial Intelligence 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; $\geq80\%$ 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. |
| title | QuantFL: Sustainable Federated Learning for Edge IoT via Pre-Trained Model Quantisation |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2603.17507 |