Resource-Aware Heterogeneous Federated Learning using Neural Architecture Search

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yu, Sixing, Muñoz, J. Pablo, Jannesari, Ali
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929332380762112
author Yu, Sixing
Muñoz, J. Pablo
Jannesari, Ali
author_facet Yu, Sixing
Muñoz, J. Pablo
Jannesari, Ali
contents Federated Learning (FL) is extensively used to train AI/ML models in distributed and privacy-preserving settings. Participant edge devices in FL systems typically contain non-independent and identically distributed (Non-IID) private data and unevenly distributed computational resources. Preserving user data privacy while optimizing AI/ML models in a heterogeneous federated network requires us to address data and system/resource heterogeneity. To address these challenges, we propose Resource-aware Federated Learning (RaFL). RaFL allocates resource-aware specialized models to edge devices using Neural Architecture Search (NAS) and allows heterogeneous model architecture deployment by knowledge extraction and fusion. Combining NAS and FL enables on-demand customized model deployment for resource-diverse edge devices. Furthermore, we propose a multi-model architecture fusion scheme allowing the aggregation of the distributed learning results. Results demonstrate RaFL's superior resource efficiency compared to SoTA.
format Preprint
id arxiv_https___arxiv_org_abs_2211_05716
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Resource-Aware Heterogeneous Federated Learning using Neural Architecture Search
Yu, Sixing
Muñoz, J. Pablo
Jannesari, Ali
Machine Learning
Computer Vision and Pattern Recognition
Federated Learning (FL) is extensively used to train AI/ML models in distributed and privacy-preserving settings. Participant edge devices in FL systems typically contain non-independent and identically distributed (Non-IID) private data and unevenly distributed computational resources. Preserving user data privacy while optimizing AI/ML models in a heterogeneous federated network requires us to address data and system/resource heterogeneity. To address these challenges, we propose Resource-aware Federated Learning (RaFL). RaFL allocates resource-aware specialized models to edge devices using Neural Architecture Search (NAS) and allows heterogeneous model architecture deployment by knowledge extraction and fusion. Combining NAS and FL enables on-demand customized model deployment for resource-diverse edge devices. Furthermore, we propose a multi-model architecture fusion scheme allowing the aggregation of the distributed learning results. Results demonstrate RaFL's superior resource efficiency compared to SoTA.
title Resource-Aware Heterogeneous Federated Learning using Neural Architecture Search
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2211.05716