Learn More by Using Less: Distributed Learning with Energy-Constrained Devices
| Title: | Learn More by Using Less: Distributed Learning with Energy-Constrained Devices |
|---|---|
| Authors: | Pereira, Roberto, Vaca-Rubio, Cristian J., Blanco, Luis |
| Publication Year: | 2024 |
| Collection: | Computer Science |
| Subject Terms: | Computer Science - Machine Learning, Computer Science - Distributed, Parallel, and Cluster Computing, Electrical Engineering and Systems Science - Signal Processing |
| More Details: | Federated Learning (FL) has emerged as a solution for distributed model training across decentralized, privacy-preserving devices, but the different energy capacities of participating devices (system heterogeneity) constrain real-world implementations. These energy limitations not only reduce model accuracy but also increase dropout rates, impacting on convergence in practical FL deployments. In this work, we propose LeanFed, an energy-aware FL framework designed to optimize client selection and training workloads on battery-constrained devices. LeanFed leverages adaptive data usage by dynamically adjusting the fraction of local data each device utilizes during training, thereby maximizing device participation across communication rounds while ensuring they do not run out of battery during the process. We rigorously evaluate LeanFed against traditional FedAvg on CIFAR-10 and CIFAR-100 datasets, simulating various levels of data heterogeneity and device participation rates. Results show that LeanFed consistently enhances model accuracy and stability, particularly in settings with high data heterogeneity and limited battery life, by mitigating client dropout and extending device availability. This approach demonstrates the potential of energy-efficient, privacy-preserving FL in real-world, large-scale applications, setting a foundation for robust and sustainable pervasive AI on resource-constrained networks. |
| Document Type: | Working Paper |
| Access URL: | http://arxiv.org/abs/2412.02289 |
| Accession Number: | edsarx.2412.02289 |
| Database: | arXiv |
| FullText | Text: Availability: 0 CustomLinks: – Url: http://arxiv.org/abs/2412.02289 Name: EDS - Arxiv Category: fullText Text: View this record from Arxiv MouseOverText: View this record from Arxiv – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsarx&genre=article&issn=&ISBN=&volume=&issue=&date=20241203&spage=&pages=&title=Learn More by Using Less: Distributed Learning with Energy-Constrained Devices&atitle=Learn%20More%20by%20Using%20Less%3A%20Distributed%20Learning%20with%20Energy-Constrained%20Devices&aulast=Pereira%2C%20Roberto&id=DOI: Name: Full Text Finder (for New FTF UI) (s8985755) Category: fullText Text: Find It @ SCU Libraries MouseOverText: Find It @ SCU Libraries |
|---|---|
| Header | DbId: edsarx DbLabel: arXiv An: edsarx.2412.02289 RelevancyScore: 1128 AccessLevel: 3 PubType: Report PubTypeId: report PreciseRelevancyScore: 1128.04357910156 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Learn More by Using Less: Distributed Learning with Energy-Constrained Devices – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Pereira%2C+Roberto%22">Pereira, Roberto</searchLink><br /><searchLink fieldCode="AR" term="%22Vaca-Rubio%2C+Cristian+J%2E%22">Vaca-Rubio, Cristian J.</searchLink><br /><searchLink fieldCode="AR" term="%22Blanco%2C+Luis%22">Blanco, Luis</searchLink> – Name: DatePubCY Label: Publication Year Group: Date Data: 2024 – Name: Subset Label: Collection Group: HoldingsInfo Data: Computer Science – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Computer+Science+-+Machine+Learning%22">Computer Science - Machine Learning</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Science+-+Distributed%2C+Parallel%2C+and+Cluster+Computing%22">Computer Science - Distributed, Parallel, and Cluster Computing</searchLink><br /><searchLink fieldCode="DE" term="%22Electrical+Engineering+and+Systems+Science+-+Signal+Processing%22">Electrical Engineering and Systems Science - Signal Processing</searchLink> – Name: Abstract Label: Description Group: Ab Data: Federated Learning (FL) has emerged as a solution for distributed model training across decentralized, privacy-preserving devices, but the different energy capacities of participating devices (system heterogeneity) constrain real-world implementations. These energy limitations not only reduce model accuracy but also increase dropout rates, impacting on convergence in practical FL deployments. In this work, we propose LeanFed, an energy-aware FL framework designed to optimize client selection and training workloads on battery-constrained devices. LeanFed leverages adaptive data usage by dynamically adjusting the fraction of local data each device utilizes during training, thereby maximizing device participation across communication rounds while ensuring they do not run out of battery during the process. We rigorously evaluate LeanFed against traditional FedAvg on CIFAR-10 and CIFAR-100 datasets, simulating various levels of data heterogeneity and device participation rates. Results show that LeanFed consistently enhances model accuracy and stability, particularly in settings with high data heterogeneity and limited battery life, by mitigating client dropout and extending device availability. This approach demonstrates the potential of energy-efficient, privacy-preserving FL in real-world, large-scale applications, setting a foundation for robust and sustainable pervasive AI on resource-constrained networks. – Name: TypeDocument Label: Document Type Group: TypDoc Data: Working Paper – Name: URL Label: Access URL Group: URL Data: <link linkTarget="URL" linkTerm="http://arxiv.org/abs/2412.02289" linkWindow="_blank">http://arxiv.org/abs/2412.02289</link> – Name: AN Label: Accession Number Group: ID Data: edsarx.2412.02289 |
| PLink | https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.2412.02289 |
| RecordInfo | BibRecord: BibEntity: Subjects: – SubjectFull: Computer Science - Machine Learning Type: general – SubjectFull: Computer Science - Distributed, Parallel, and Cluster Computing Type: general – SubjectFull: Electrical Engineering and Systems Science - Signal Processing Type: general Titles: – TitleFull: Learn More by Using Less: Distributed Learning with Energy-Constrained Devices Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Pereira, Roberto – PersonEntity: Name: NameFull: Vaca-Rubio, Cristian J. – PersonEntity: Name: NameFull: Blanco, Luis IsPartOfRelationships: – BibEntity: Dates: – D: 03 M: 12 Type: published Y: 2024 |
| ResultId | 1 |