期刊
IEEE WIRELESS COMMUNICATIONS LETTERS
卷 11, 期 10, 页码 2180-2184出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LWC.2022.3196241
关键词
Wireless sensor networks; Convergence; Channel allocation; Machine learning; Internet of Things; Data models; Wireless communication; Federated learning; sparsification; multi-channel aloha; wireless sensor networks
资金
- CNPq, Brazil [402378/20210, 305021/2021-4, 307226/2021-2, 164300/2021-0]
- RNP/MCTIC, Brazil (6G Mobile Communications Systems) [01245.010604/2020-14]
- Australian Government through the Australian Research Council's Discovery Projects Funding Scheme [DP200100391]
This paper proposes an optimal method for allocating wireless resources in a multi-channel ALOHA setup, which outperforms uniform and fully-shared channel allocations in terms of convergence time in large-scale wireless sensor networks involving decentralized machine learning.
Large-scale wireless sensor networks are instrumental for several Internet of Things (IoT) applications involving data analytics and machine learning. The huge data volume generated by such networks imposes a change of paradigm from centralized machine learning to decentralized. Federated Learning (FL) is a well-known type of decentralized machine learning, whose efficiency heavily depends on the use of wireless communication resources. Random Access (RA) protocols, such as ALOHA, despite their simplicity, can improve the convergence time of FL systems if multiple orthogonal channels are used. This letter considers that devices are involved in the optimization of more than one model in a FL system, and then proposes an optimum method to allocate wireless resources in a multi-channel ALOHA setup. The proposed method outperforms uniform and fully-shared channel allocations in terms of convergence time.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据