Fast converging Federated Learning with Non-IID Data
Loading...
Access rights
openAccess
acceptedVersion
URL
Journal Title
Journal ISSN
Volume Title
A4 Artikkeli konferenssijulkaisussa
This publication is imported from Aalto University research portal.
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
Authors
Date
2023
Major/Subject
Mcode
Degree programme
Language
en
Pages
Series
2023 IEEE 97th Vehicular Technology Conference, VTC 2023-Spring - Proceedings, IEEE Vehicular Technology Conference ; Volume 2023-June
Abstract
With the advancement of device capabilities, Internet of Things (IoT) devices can employ built-in hardware to perform machine learning (ML) tasks, extending their horizons in many promising directions. In traditional ML, data are sent to a server for training. However, this approach raises user privacy concerns. On the other hand, transferring user data to a cloud-centric environment results in increased latency. A decentralized ML technique, Federated learning (FL), has been proposed to enable devices to train locally on personal data and then send the data to a server for model aggregation. In these models, malicious devices, or devices with a minor contribution to a global model, increase communication rounds and resource usage. Likewise, heterogeneous data, such as non-independent and identically distributed (Non-IID), may decrease accuracy of the FL model. This paper proposes a mechanism to quantify device contributions based on weight divergence. We propose an outlier-removal approach which identifies irrelevant device updates. Client selection probabilities are computed using a Bayesian model. To obtain a global model, we employ a novel merging algorithm utilizing weight shifting values to ensure convergence towards more accurate predictions. A simulation using the MNIST dataset employing both non-iid and iid devices, distributed on 10 Jetson Nano devices, shows that our approach converges faster, significantly reduces communication cost, and improves accuracy.Description
Publisher Copyright: © 2023 IEEE.
Keywords
communication reduction, edge computing, Federated learning, fog networks, Internet of things, non-iid data
Other note
Citation
Naas, S A & Sigg, S 2023, Fast converging Federated Learning with Non-IID Data . in 2023 IEEE 97th Vehicular Technology Conference, VTC 2023-Spring - Proceedings . IEEE Vehicular Technology Conference, vol. 2023-June, IEEE, IEEE Vehicular Technology Conference, Florence, Italy, 20/06/2023 . https://doi.org/10.1109/VTC2023-Spring57618.2023.10200108