https://scholars.lib.ntu.edu.tw/handle/123456789/611210
標題: | Online Extreme Learning Machine Design for the Application of Federated Learning | 作者: | AN-YEU(ANDY) WU | 關鍵字: | Federated learning; online sequential extreme learning machine | 公開日期: | 2020 | 起(迄)頁: | 188-192 | 來源出版物: | Proceedings - 2020 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2020 | 摘要: | In this paper, we propose a federated extreme learning machine system (Fed-ELMS) to meet the demand for federated learning scenarios. In the scenario of federated learning, data is kept on edge devices to preserve the privacy of data, while metadata, such as model parameters, are exchanged between a centralized cloud server and edge devices. Despite non-independent and identically distributed (non-IID) and imbalanced data across edge devices, we show that Fed-ELMS can still achieve comparable performance with only 3.3% accuracy loss compared to a centralized ELM trained with IID and balanced data. (a) Moreover, by quantizing input weights and biases, parameters of a model and transmission power consumption between cloud and edge are dramatically reduced. Compared With conventional neural networks (NNs) with the same transmission cost, the proposed Fed-ELMS outperforms FederatedAveraging NN (Fed- NN) by 2.3% accuracy and the fine-tuning process is 7%-33% less time-consuming. Therefore, the proposed Fed-ELMS is a promising system for edge devices to support the future trend of federated learning. © 2020 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85084986459&doi=10.1109%2fAICAS48895.2020.9073802&partnerID=40&md5=0d6ba8a8386b81c07402ab393049e312 https://scholars.lib.ntu.edu.tw/handle/123456789/611210 |
ISBN: | 9.78173E+12 | DOI: | 10.1109/AICAS48895.2020.9073802 | SDG/關鍵字: | Data privacy; Green computing; Knowledge acquisition; Machine design; Machine learning; Extreme learning machine; Future trends; Imbalanced data; Learning scenarios; Model parameters; Neural networks (NNS); Transmission costs; Transmission power; E-learning |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。