动量(技术分析)
趋同(经济学)
计算机科学
加速度
GSM演进的增强数据速率
航程(航空)
云计算
适应(眼睛)
主流
上下界
人工智能
数学
物理
工程类
航空航天工程
神学
光学
财务
经典力学
经济
经济增长
操作系统
数学分析
哲学
作者
Zhengjie Yang,Shuai Fu,Wei Bao,Dong Yuan,Bing Bing Zhou
标识
DOI:10.1109/icdcs57875.2023.00053
摘要
In this paper, we propose and analyze HierAdMo, a three-tier adaptive momentum accelerated client-edge-cloud Federated Learning (FL) algorithm. HierAdMo combines the momentum acceleration on both worker and edge levels. However, simply combining these two levels of momenta may lead to disagreement between them, negatively influencing convergence performance. To this end, we embed an online adaptive method that scales down the momentum when disagreement occurs. We provide mathematical proof for the convergence of HierAdMo for non-i.i.d. data and the tighter convergence upper bound compared with a version of HierAdMo without adaptation (HierAdMo-R). Finally, extensive experiments based on real-world datasets are conducted, verifying that HierAdMo outperforms existing mainstream benchmarks and achieves the optimal or near-optimal convergence performance compared with HierAdMo-R under a wide range of settings.
科研通智能强力驱动
Strongly Powered by AbleSci AI