dc.contributor.author
Gulati, Mayank
dc.contributor.author
Zandberg, Koen
dc.contributor.author
Huang, Zhaolan
dc.contributor.author
Wunder, Gerhard
dc.contributor.author
Adjih, Cedric
dc.contributor.author
Baccelli, Emmanuel
dc.date.accessioned
2025-01-13T10:09:57Z
dc.date.available
2025-01-13T10:09:57Z
dc.identifier.uri
https://refubium.fu-berlin.de/handle/fub188/46212
dc.identifier.uri
http://dx.doi.org/10.17169/refubium-45924
dc.description.abstract
More and more, edge devices embark Artificial Neuron Networks. In this context, a trend is to simultaneously decentralize their training as much as possible while shrinking their resource requirements, both for inference and training—tasks that are typically intensive in terms of data, memory, and computation. At the edge’s extremity, a specific challenge arises concerning the inclusion of microcontroller-based devices typically deployed in the IoT. So far, no general framework has been provided for that. Such devices not only have extremely challenging resource constraints (weak CPUs, slow network connections, memory budgets measured in kilobytes) but also exhibit high polymorphism, leading to large variability in computational performance among these devices. In this paper, we design and implement TDMiL, a versatile framework for distributed training, and transfer learning. TDMiL interconnects and combines logical components including CoAPerator (a central aggregator) and various tiny embedded software runtimes that are specifically tailored for networks comprising heterogeneous, resource-constrained devices built on diverse types of microcontrollers. We report on experiments conducted with the TDMiL framework, which we use to comparatively evaluate several schemes devised to address computational variability among distributed learning microcontroller-based devices, i.e., stragglers. Additionally, we release the code of our implementation of TDMiL as an open-source project, which is compatible with common commercial off-the-shelf IoT hardware and a well-known open-access IoT testbed.
en
dc.format.extent
17 Seiten
dc.rights.uri
https://creativecommons.org/licenses/by/4.0/
dc.subject
Distributed learning
en
dc.subject
federated learning (FL)
en
dc.subject
Internet of Things (IoT)
en
dc.subject
machine learning
en
dc.subject
microcontrollers
en
dc.subject
TinyML-as-a-Service (TMLaaS)
en
dc.subject.ddc
000 Informatik, Informationswissenschaft, allgemeine Werke::000 Informatik, Wissen, Systeme::004 Datenverarbeitung; Informatik
dc.title
TDMiL: Tiny Distributed Machine Learning for Microcontroller-Based Interconnected Devices
dc.type
Wissenschaftlicher Artikel
dcterms.bibliographicCitation.doi
10.1109/ACCESS.2024.3492921
dcterms.bibliographicCitation.journaltitle
IEEE Access
dcterms.bibliographicCitation.pagestart
167810
dcterms.bibliographicCitation.pageend
167826
dcterms.bibliographicCitation.volume
12
dcterms.bibliographicCitation.url
https://doi.org/10.1109/ACCESS.2024.3492921
refubium.affiliation
Mathematik und Informatik
refubium.affiliation.other
Institut für Informatik
refubium.resourceType.isindependentpub
no
dcterms.accessRights.openaire
open access
dcterms.isPartOf.eissn
2169-3536
refubium.resourceType.provider
WoS-Alert