Guardado en:
Detalles Bibliográficos
Autores principales: Tun, Ye Lin, Thwal, Chu Myaet, Le, Huy Q., Nguyen, Minh N. H., Huh, Eui-Nam, Hong, Choong Seon
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2401.11647
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915645763878912
author Tun, Ye Lin
Thwal, Chu Myaet
Le, Huy Q.
Nguyen, Minh N. H.
Huh, Eui-Nam
Hong, Choong Seon
author_facet Tun, Ye Lin
Thwal, Chu Myaet
Le, Huy Q.
Nguyen, Minh N. H.
Huh, Eui-Nam
Hong, Choong Seon
contents Many studies integrate federated learning (FL) with self-supervised learning (SSL) to take advantage of raw data distributed across edge devices. However, edge devices often struggle with high computational and communication costs imposed by SSL and FL algorithms. With the deployment of more complex and large-scale models, these challenges are exacerbated. To tackle this, we propose Layer-Wise Federated Self-Supervised Learning (LW-FedSSL), which allows edge devices to incrementally train a small part of the model at a time. Specifically, in LW-FedSSL, training is decomposed into multiple stages, with each stage responsible for only a specific layer of the model. Since only a portion of the model is active for training at any given time, LW-FedSSL significantly reduces computational requirements. Additionally, only the active model portion needs to be exchanged between the FL server and clients, reducing communication overhead. This enables LW-FedSSL to jointly address both computational and communication challenges of FL client devices. It can achieve up to a $3.34 \times$ reduction in memory usage, $4.20 \times$ fewer computational operations (giga floating point operations, GFLOPs), and a $5.07 \times$ lower communication cost while maintaining performance comparable to its end-to-end training counterpart. Furthermore, we explore a progressive training strategy called Progressive Federated Self-Supervised Learning (Prog-FedSSL), which offers a $1.84\times$ reduction in GFLOPs and a $1.67\times$ reduction in communication costs while maintaining the same memory requirements as end-to-end training. Although the resource efficiency of Prog-FedSSL is lower than that of LW-FedSSL, its performance improvements make it a viable candidate for FL environments with more lenient resource constraints.
format Preprint
id arxiv_https___arxiv_org_abs_2401_11647
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Resource-efficient Layer-wise Federated Self-supervised Learning
Tun, Ye Lin
Thwal, Chu Myaet
Le, Huy Q.
Nguyen, Minh N. H.
Huh, Eui-Nam
Hong, Choong Seon
Machine Learning
Artificial Intelligence
Many studies integrate federated learning (FL) with self-supervised learning (SSL) to take advantage of raw data distributed across edge devices. However, edge devices often struggle with high computational and communication costs imposed by SSL and FL algorithms. With the deployment of more complex and large-scale models, these challenges are exacerbated. To tackle this, we propose Layer-Wise Federated Self-Supervised Learning (LW-FedSSL), which allows edge devices to incrementally train a small part of the model at a time. Specifically, in LW-FedSSL, training is decomposed into multiple stages, with each stage responsible for only a specific layer of the model. Since only a portion of the model is active for training at any given time, LW-FedSSL significantly reduces computational requirements. Additionally, only the active model portion needs to be exchanged between the FL server and clients, reducing communication overhead. This enables LW-FedSSL to jointly address both computational and communication challenges of FL client devices. It can achieve up to a $3.34 \times$ reduction in memory usage, $4.20 \times$ fewer computational operations (giga floating point operations, GFLOPs), and a $5.07 \times$ lower communication cost while maintaining performance comparable to its end-to-end training counterpart. Furthermore, we explore a progressive training strategy called Progressive Federated Self-Supervised Learning (Prog-FedSSL), which offers a $1.84\times$ reduction in GFLOPs and a $1.67\times$ reduction in communication costs while maintaining the same memory requirements as end-to-end training. Although the resource efficiency of Prog-FedSSL is lower than that of LW-FedSSL, its performance improvements make it a viable candidate for FL environments with more lenient resource constraints.
title Resource-efficient Layer-wise Federated Self-supervised Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2401.11647