通信高效联邦学习中客户端选择的自适应聚类方案

Yan-Ann Chen, Guangpu Chen
{"title":"通信高效联邦学习中客户端选择的自适应聚类方案","authors":"Yan-Ann Chen, Guangpu Chen","doi":"10.1109/APWCS60142.2023.10234043","DOIUrl":null,"url":null,"abstract":"Federated learning is a novel decentralized learning architecture. During the training process, the client and server must continuously upload and receive model parameters, which consumes a lot of network transmission resources. Some methods use clustering to find more representative customers, select only a part of them for training, and at the same time ensure the accuracy of training. However, in federated learning, it is not trivial to know what the number of clusters can bring the best training result. Therefore, we propose to dynamically adjust the number of clusters to find the most ideal grouping results. It may reduce the number of users participating in the training to achieve the effect of reducing communication costs without affecting the model performance. We verify its experimental results on the non-IID handwritten digit recognition dataset and reduce the cost of communication and transmission by almost 50% compared with traditional federated learning without affecting the accuracy of the model.","PeriodicalId":375211,"journal":{"name":"2023 VTS Asia Pacific Wireless Communications Symposium (APWCS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"An Adaptive Clustering Scheme for Client Selections in Communication-Efficient Federated Learning\",\"authors\":\"Yan-Ann Chen, Guangpu Chen\",\"doi\":\"10.1109/APWCS60142.2023.10234043\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Federated learning is a novel decentralized learning architecture. During the training process, the client and server must continuously upload and receive model parameters, which consumes a lot of network transmission resources. Some methods use clustering to find more representative customers, select only a part of them for training, and at the same time ensure the accuracy of training. However, in federated learning, it is not trivial to know what the number of clusters can bring the best training result. Therefore, we propose to dynamically adjust the number of clusters to find the most ideal grouping results. It may reduce the number of users participating in the training to achieve the effect of reducing communication costs without affecting the model performance. We verify its experimental results on the non-IID handwritten digit recognition dataset and reduce the cost of communication and transmission by almost 50% compared with traditional federated learning without affecting the accuracy of the model.\",\"PeriodicalId\":375211,\"journal\":{\"name\":\"2023 VTS Asia Pacific Wireless Communications Symposium (APWCS)\",\"volume\":\"22 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 VTS Asia Pacific Wireless Communications Symposium (APWCS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/APWCS60142.2023.10234043\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 VTS Asia Pacific Wireless Communications Symposium (APWCS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/APWCS60142.2023.10234043","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

联邦学习是一种新型的分散学习体系结构。在训练过程中,客户端和服务器端必须不断地上传和接收模型参数,这消耗了大量的网络传输资源。有些方法通过聚类来寻找更具代表性的客户,只选择其中的一部分进行训练,同时保证训练的准确性。然而,在联邦学习中,知道多少聚类可以带来最好的训练结果并不是一件容易的事。因此,我们提出动态调整聚类的数量,以找到最理想的分组结果。可以在不影响模型性能的情况下,减少参与训练的用户数量,达到降低通信成本的效果。我们在非iid手写数字识别数据集上验证了其实验结果,与传统的联邦学习相比,在不影响模型准确性的情况下,将通信和传输成本降低了近50%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
An Adaptive Clustering Scheme for Client Selections in Communication-Efficient Federated Learning
Federated learning is a novel decentralized learning architecture. During the training process, the client and server must continuously upload and receive model parameters, which consumes a lot of network transmission resources. Some methods use clustering to find more representative customers, select only a part of them for training, and at the same time ensure the accuracy of training. However, in federated learning, it is not trivial to know what the number of clusters can bring the best training result. Therefore, we propose to dynamically adjust the number of clusters to find the most ideal grouping results. It may reduce the number of users participating in the training to achieve the effect of reducing communication costs without affecting the model performance. We verify its experimental results on the non-IID handwritten digit recognition dataset and reduce the cost of communication and transmission by almost 50% compared with traditional federated learning without affecting the accuracy of the model.
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