{"title":"无线应用的联合学习:原型","authors":"Varun Laxman Muttepawar, Arjun Mehra, Zubair Shaban, Ranjitha Prasad, Harshan Jagadeesh","doi":"arxiv-2312.08577","DOIUrl":null,"url":null,"abstract":"Wireless embedded edge devices are ubiquitous in our daily lives, enabling\nthem to gather immense data via onboard sensors and mobile applications. This\noffers an amazing opportunity to train machine learning (ML) models in the\nrealm of wireless devices for decision-making. Training ML models in a wireless\nsetting necessitates transmitting datasets collected at the edge to a cloud\nparameter server, which is infeasible due to bandwidth constraints, security,\nand privacy issues. To tackle these challenges, Federated Learning (FL) has\nemerged as a distributed optimization approach to the decentralization of the\nmodel training process. In this work, we present a novel prototype to examine\nFL's effectiveness over bandwidth-constrained wireless channels. Through a\nnovel design consisting of Zigbee and NI USRP devices, we propose a\nconfiguration that allows clients to broadcast synergistically local ML model\nupdates to a central server to obtain a generalized global model. We assess the\nefficacy of this prototype using metrics such as global model accuracy and time\ncomplexity under varying conditions of transmission power, data heterogeneity\nand local learning.","PeriodicalId":501433,"journal":{"name":"arXiv - CS - Information Theory","volume":"33 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2023-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Federated Learning for Wireless Applications: A Prototype\",\"authors\":\"Varun Laxman Muttepawar, Arjun Mehra, Zubair Shaban, Ranjitha Prasad, Harshan Jagadeesh\",\"doi\":\"arxiv-2312.08577\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Wireless embedded edge devices are ubiquitous in our daily lives, enabling\\nthem to gather immense data via onboard sensors and mobile applications. This\\noffers an amazing opportunity to train machine learning (ML) models in the\\nrealm of wireless devices for decision-making. Training ML models in a wireless\\nsetting necessitates transmitting datasets collected at the edge to a cloud\\nparameter server, which is infeasible due to bandwidth constraints, security,\\nand privacy issues. To tackle these challenges, Federated Learning (FL) has\\nemerged as a distributed optimization approach to the decentralization of the\\nmodel training process. In this work, we present a novel prototype to examine\\nFL's effectiveness over bandwidth-constrained wireless channels. Through a\\nnovel design consisting of Zigbee and NI USRP devices, we propose a\\nconfiguration that allows clients to broadcast synergistically local ML model\\nupdates to a central server to obtain a generalized global model. We assess the\\nefficacy of this prototype using metrics such as global model accuracy and time\\ncomplexity under varying conditions of transmission power, data heterogeneity\\nand local learning.\",\"PeriodicalId\":501433,\"journal\":{\"name\":\"arXiv - CS - Information Theory\",\"volume\":\"33 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-12-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Information Theory\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2312.08577\",\"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 - CS - Information Theory","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2312.08577","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
无线嵌入式边缘设备在我们的日常生活中无处不在,使它们能够通过板载传感器和移动应用程序收集大量数据。这为在无线设备中训练机器学习(ML)模型以进行决策提供了绝佳的机会。在无线环境中训练 ML 模型需要将在边缘收集的数据集传输到云参数服务器,但由于带宽限制、安全和隐私问题,这种做法并不可行。为了应对这些挑战,联邦学习(FL)作为一种分布式优化方法应运而生,它可以实现模型训练过程的去中心化。在这项工作中,我们提出了一个新颖的原型,以检验联邦学习在带宽受限的无线信道中的有效性。通过一个由 Zigbee 和 NI USRP 设备组成的新颖设计,我们提出了一种配置,允许客户端向中央服务器协同广播本地 ML 模型更新,从而获得一个广义的全局模型。我们在不同的传输功率、数据异构性和本地学习条件下,使用全局模型准确性和时间复杂性等指标来评估该原型的有效性。
Federated Learning for Wireless Applications: A Prototype
Wireless embedded edge devices are ubiquitous in our daily lives, enabling
them to gather immense data via onboard sensors and mobile applications. This
offers an amazing opportunity to train machine learning (ML) models in the
realm of wireless devices for decision-making. Training ML models in a wireless
setting necessitates transmitting datasets collected at the edge to a cloud
parameter server, which is infeasible due to bandwidth constraints, security,
and privacy issues. To tackle these challenges, Federated Learning (FL) has
emerged as a distributed optimization approach to the decentralization of the
model training process. In this work, we present a novel prototype to examine
FL's effectiveness over bandwidth-constrained wireless channels. Through a
novel design consisting of Zigbee and NI USRP devices, we propose a
configuration that allows clients to broadcast synergistically local ML model
updates to a central server to obtain a generalized global model. We assess the
efficacy of this prototype using metrics such as global model accuracy and time
complexity under varying conditions of transmission power, data heterogeneity
and local learning.