QuantFL: Sustainable Federated Learning for Edge IoT via Pre-Trained Model Quantisation

Charuka Herath; Yogachandran Rahulamathavan; Varuna De Silva; Sangarapillai Lambotharan

cs.LGMar 18, 2026

QuantFL: Sustainable Federated Learning for Edge IoT via Pre-Trained Model Quantisation

Authors: Charuka Herath, Yogachandran Rahulamathavan, Varuna De Silva, Sangarapillai Lambotharan

Organizations: Institute of Digital Technologies, Loughborough University, UK

Abstract

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.

Figures & tables

Symbol	Description
$N,\mathcal{S}_{k}$	Total clients, Selected subset at round $k$
$w^{k},w_{i}^{k}$	Global model, Local model of client $i$
$\Delta w$	Model update ( $w_{i}^{k}-w^{k}$ )
$L_{l},\mathcal{B}_{l}$	Quantization levels, Codebook boundaries for layer $l$
$T_{l}$ , $\alpha$	Codebook refresh period, Dirichlet-sweeps

TABLE I: List of Notations

Fig. 1: QuantFL pipeline. Each client quantises its per-layer update using BU (equal-width) or BQ (equal-mass) buckets and sends only indices ; boundaries are refreshed infrequently. The server applies mid-point decoding and aggregates. Pre-training makes updates narrowly distributed, enabling aggressive compression with little error.

w^{k+1}\;=\;w^{k}+\frac{1}{|\mathcal{S}_{k}|}\sum_{i\in\mathcal{S}_{k}}\tilde{w}_{i,k}

Algorithm 1 Federated Learning with Bucketed Update Quantisation ( QuantFL )

Dataset	Method	Train Accuracy	Train Loss	Test Accuracy	Test Loss	Comm. Cost (64 / 128)	↓ vs NQ
MNIST	Baseline (NQ, NP)	90.37%	0.2760	90.01%	0.1789	3,494,400	-
	BQ (Ours)	78.84%	0.7964	77.67%	0.3452	2,074,903 / 2,129,605	40.62% / 39.06%
	BU (Ours)	89.18%	0.5376	89.00%	0.2407	2,074,903 / 2,129,605	40.62% / 39.06%
	QSGD	83.44%	0.6121	82.89%	0.2340	2,129,560 / 2,184,160	39.06% / 37.50%
	BU (NP)	70.45%	0.8421	69.78%	0.4020	2,074,903 / 2,129,605	40.62% / 39.06%
	BQ (NP)	78.12%	0.5910	77.32%	0.2950	2,074,903 / 2,129,605	40.62% / 39.06%

TABLE II: Training and Test Results with Communication Costs on MNIST and CIFAR-100. NQ - non-quantised, NP - not-pre-trained, Bucket-Quantile (BQ), Bucket-Uniform (BU)

$\boldsymbol{\alpha}$	BU Acc (%)	BQ Acc (%)	QSGD Acc (%)
1.0	68.28	31.0	31.8
0.5	66.89	25.78	28.90
0.1	52.1	23.4	27.1

TABLE III: Non-IID robustness on CIFAR-100 with Dirichlet heterogeneity (

L{=}64

). Smaller

\alpha

= stronger skew.

Fig. 2: Update concentration with pre-training vs. training from scratch (simulated illustration). Pre-trained updates exhibit substantially smaller dynamic range R and variance, and reduced kurtosis (shorter tails), enabling lower quantisation error at fixed L.

Panel of Figure 7 — Fig. 3: Training loss and test accuracy curves for MNIST and CIFAR-100 under different quantisation methods. Baseline FedAvg is a non-quantised and non-pre-trained setting.

Fig. 4: Test accuracy vs. total bits per round (per client; uplink+downlink; log x-axis) on MNIST and CIFAR-100. Downlink is full-precision in all points unless stated.

Explore similar work

Quantization in Federated Learning: Methods, Challenges and Future Directions
Jun 25, 2026Farwa Ikram, Dipanwita Thakur, Antonella Guzzo +1Neural Network Quantization Federated Learning
DIMES - University of Calabria, Italy
Quantization Impact on the Accuracy and Communication Efficiency Trade-off in Federated Learning for Aerospace Predictive Maintenance
Apr 9, 2026Abdelkarim LoukiliFederated Learning Predictive Maintenance
GQ-FSL: Green Quantized Federated Split Learning
Jul 31, 2026Idan Roth, Lutz LampeMixed-Precision Quantization Energy-Efficient ML
The University of British Columbia, Vancouver, BC, Canada

Jun 25, 2026J/K move · Enter open · S save

Quantization in Federated Learning: Methods, Challenges and Future Directions

Farwa Ikram, Dipanwita Thakur, Antonella Guzzo, Giancarlo Fortino

DIMES - University of Calabria, Italy

Neural Network Quantization Federated Learning

Open paper AskPDF arXiv

Federated Learning (FL) has become a foundational paradigm for privacy-preserving distributed intelligence, yet its scalability remains fundamentally constrained by communication bottlenecks, device heterogeneity, and the challenges of training under statistically non-IID data. Quantization is one of the most effective mechanisms for mitigating these limitations, reducing both uplink/downlink payloads and on-device computation. This paper provides the first FL-centric systematic review of quantization, introducing a novel taxonomy organized around FL-specific dimensions, including client heterogeneity, aggregation consistency, communication-scheduling adaptation, non-IID robustness, privacy/security integration, and hardware/energy co-optimization. Beyond cataloging existing methods, we analyze how quantization interacts with core FL behaviors such as client drift, partial participation, convergence stability, secure aggregation, and differential privacy. We further identify cross-method insights, open research gaps, and design guidelines for practitioners deploying quantized FL on mobile, IoT, and edge platforms. This survey thus establishes quantization not merely as a compression technique, but as a fundamental systems component shaping the performance, robustness, and practicality of modern FL.

Abstract

Explore similar work

Quantization in Federated Learning: Methods, Challenges and Future Directions

Quantization Impact on the Accuracy and Communication Efficiency Trade-off in Federated Learning for Aerospace Predictive Maintenance

GQ-FSL: Green Quantized Federated Split Learning