自编码
计算机科学
延迟(音频)
联合学习
人工智能
架空(工程)
深度学习
调度(生产过程)
机器学习
实时计算
操作系统
电信
工程类
运营管理
作者
Chi-Kai Hsieh,Feng‐Tsun Chien,Min-Kuan Chang
标识
DOI:10.1109/apsipaasc58517.2023.10317190
摘要
This paper investigates the application of autoencoder (AE) in supporting the training process of federated learning by reducing communication overhead and latency. We propose a scheduling algorithm to determine when and how to use autoencoder during training. Our simulation shows that federated learning with an au-toencoder significantly reduces communication overhead without compromising testing accuracy. Moreover, the testing accuracy curve shows a more consistent increase over training rounds in federated learning with an autoen-coder than in federated learning without an autoencoder. Additionally, the latency of federated learning with an autoencoder is lower than that of federated learning without an autoencoder.
科研通智能强力驱动
Strongly Powered by AbleSci AI