TinyFed: Lightweight Federated Learning for Constrained IoT Devices

ABSTRACT TinyML enables machine learning inference on microcontrollers with limited resources. Extending this to a collaborative setting led to Tiny Federated Learning (TinyFL). This article presents TinyFed, a lightweight framework that supports the full federated learning cycle—from local training...

Full description

Saved in:
Bibliographic Details
Published inInternet technology letters Vol. 8; no. 4
Main Authors Silva, Claudio Jr. N., Peixoto, Maycon L. M., Figueiredo, Gustavo B., Prazeres, Cassio V. S.
Format Journal Article
LanguageEnglish
Published Chichester, UK John Wiley & Sons, Ltd 01.07.2025
Subjects
constrained devices
IoT
machine learning
neural networks
TinyFL
Online AccessGet full text
ISSN2476-1508
2476-1508
DOI10.1002/itl2.70061

Cover

More Information
Summary:ABSTRACT TinyML enables machine learning inference on microcontrollers with limited resources. Extending this to a collaborative setting led to Tiny Federated Learning (TinyFL). This article presents TinyFed, a lightweight framework that supports the full federated learning cycle—from local training to model aggregation and redistribution. TinyFed was validated on ESP32 devices using a neural network with four inputs, three hidden layers, and two outputs to detect temperature, humidity, luminosity, and voltage anomalies. Local training achieved accuracies of up to 99.47%.
ISSN:2476-1508
2476-1508
DOI:10.1002/itl2.70061