多模式无线联合学习的上行链路空中聚合

Chong Zhang, Min Dong, Ben Liang, Ali Afana, Yahia Ahmed
{"title":"多模式无线联合学习的上行链路空中聚合","authors":"Chong Zhang, Min Dong, Ben Liang, Ali Afana, Yahia Ahmed","doi":"arxiv-2409.00978","DOIUrl":null,"url":null,"abstract":"We propose an uplink over-the-air aggregation (OAA) method for wireless\nfederated learning (FL) that simultaneously trains multiple models. To maximize\nthe multi-model training convergence rate, we derive an upper bound on the\noptimality gap of the global model update, and then, formulate an uplink joint\ntransmit-receive beamforming optimization problem to minimize this upper bound.\nWe solve this problem using the block coordinate descent approach, which admits\nlow-complexity closed-form updates. Simulation results show that our proposed\nmulti-model FL with fast OAA substantially outperforms sequentially training\nmultiple models under the conventional single-model approach.","PeriodicalId":501082,"journal":{"name":"arXiv - MATH - Information Theory","volume":"20 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Uplink Over-the-Air Aggregation for Multi-Model Wireless Federated Learning\",\"authors\":\"Chong Zhang, Min Dong, Ben Liang, Ali Afana, Yahia Ahmed\",\"doi\":\"arxiv-2409.00978\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We propose an uplink over-the-air aggregation (OAA) method for wireless\\nfederated learning (FL) that simultaneously trains multiple models. To maximize\\nthe multi-model training convergence rate, we derive an upper bound on the\\noptimality gap of the global model update, and then, formulate an uplink joint\\ntransmit-receive beamforming optimization problem to minimize this upper bound.\\nWe solve this problem using the block coordinate descent approach, which admits\\nlow-complexity closed-form updates. Simulation results show that our proposed\\nmulti-model FL with fast OAA substantially outperforms sequentially training\\nmultiple models under the conventional single-model approach.\",\"PeriodicalId\":501082,\"journal\":{\"name\":\"arXiv - MATH - Information Theory\",\"volume\":\"20 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - MATH - Information Theory\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.00978\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - MATH - Information Theory","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.00978","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

我们为无线联合学习(FL)提出了一种可同时训练多个模型的上行链路空中聚合(OAA)方法。为了最大限度地提高多模型训练收敛率,我们推导出了全局模型更新最优性差距的上界,然后提出了一个上行链路联合发射接收波束成形优化问题,以最小化该上界。仿真结果表明,我们提出的具有快速 OAA 的多模型 FL 大大优于传统单模型方法下的多模型顺序训练。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Uplink Over-the-Air Aggregation for Multi-Model Wireless Federated Learning
We propose an uplink over-the-air aggregation (OAA) method for wireless federated learning (FL) that simultaneously trains multiple models. To maximize the multi-model training convergence rate, we derive an upper bound on the optimality gap of the global model update, and then, formulate an uplink joint transmit-receive beamforming optimization problem to minimize this upper bound. We solve this problem using the block coordinate descent approach, which admits low-complexity closed-form updates. Simulation results show that our proposed multi-model FL with fast OAA substantially outperforms sequentially training multiple models under the conventional single-model approach.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信