FedMeld: A Model-dispersal Federated Learning Framework for Space-ground Integrated Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Qian, Chen, Xianhao, Huang, Kaibin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918259856506880
author Chen, Qian
Chen, Xianhao
Huang, Kaibin
author_facet Chen, Qian
Chen, Xianhao
Huang, Kaibin
contents To bridge the digital divide, space-ground integrated networks (SGINs) are expected to deliver artificial intelligence (AI) services to every corner of the world. One key mission of SGINs is to support federated learning (FL) at a global scale. However, existing space-ground integrated FL frameworks involve ground stations or costly inter-satellite links, entailing excessive training latency and communication costs. To overcome these limitations, we propose an infrastructure-free federated learning framework based on a model dispersal (FedMeld) strategy, which exploits periodic movement patterns and store-carry-forward capabilities of satellites to enable parameter mixing across large-scale geographical regions. We theoretically show that FedMeld leads to global model convergence and quantify the effects of round interval and mixing ratio between adjacent areas on its learning performance. Based on the theoretical results, we formulate a joint optimization problem to design the staleness control and mixing ratio (SC-MR) for minimizing the training loss. By decomposing the problem into sequential SC and MR subproblems without compromising the optimality, we derive the round interval solution in a closed form and the mixing ratio in a semi-closed form to achieve the optimal latency-accuracy tradeoff. Experiments using various datasets demonstrate that FedMeld achieves superior model accuracy while significantly reducing communication costs as compared with traditional FL schemes for SGINs.
format Preprint
id arxiv_https___arxiv_org_abs_2412_17231
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FedMeld: A Model-dispersal Federated Learning Framework for Space-ground Integrated Networks
Chen, Qian
Chen, Xianhao
Huang, Kaibin
Machine Learning
Information Theory
Networking and Internet Architecture
To bridge the digital divide, space-ground integrated networks (SGINs) are expected to deliver artificial intelligence (AI) services to every corner of the world. One key mission of SGINs is to support federated learning (FL) at a global scale. However, existing space-ground integrated FL frameworks involve ground stations or costly inter-satellite links, entailing excessive training latency and communication costs. To overcome these limitations, we propose an infrastructure-free federated learning framework based on a model dispersal (FedMeld) strategy, which exploits periodic movement patterns and store-carry-forward capabilities of satellites to enable parameter mixing across large-scale geographical regions. We theoretically show that FedMeld leads to global model convergence and quantify the effects of round interval and mixing ratio between adjacent areas on its learning performance. Based on the theoretical results, we formulate a joint optimization problem to design the staleness control and mixing ratio (SC-MR) for minimizing the training loss. By decomposing the problem into sequential SC and MR subproblems without compromising the optimality, we derive the round interval solution in a closed form and the mixing ratio in a semi-closed form to achieve the optimal latency-accuracy tradeoff. Experiments using various datasets demonstrate that FedMeld achieves superior model accuracy while significantly reducing communication costs as compared with traditional FL schemes for SGINs.
title FedMeld: A Model-dispersal Federated Learning Framework for Space-ground Integrated Networks
topic Machine Learning
Information Theory
Networking and Internet Architecture
url https://arxiv.org/abs/2412.17231