Scalable and Low-Latency Federated Learning With Cooperative Mobile Edge Networking
Scalable and Low-Latency Federated Learning With Cooperative Mobile Edge Networking
复制标题
DOI：
10.1109/tmc.2022.3216837
复制
发表时间：
2022-05
影响因子：
7.9
通讯作者：
Zhenxiao Zhang;Zhidong Gao;Yuanxiong Guo;Yanmin Gong
中科院分区：
文献类型：
--
作者：
Zhenxiao Zhang;Zhidong Gao;Yuanxiong Guo;Yanmin Gong
联邦学习（FL）支持协作模型训练，而无需集中数据。然而，传统的FL框架是基于云的，并且具有高通信延迟。另一方面，依赖于与移动的基站共置的边缘服务器用于模型聚合的基于边缘的FL框架具有低通信延迟，但是由于边缘服务器的有限覆盖而遭受降级的模型准确性。针对基于云的高精度高延迟FL和基于边缘的低延迟低精度FL，提出一种基于协作移动的边缘网络的FL框架--协作联邦边缘学习（CFEL），以实现移动的边缘网络的高精度和低延迟分布式智能。考虑到CFEL独特的两层网络架构，进一步开发了一种新的联邦优化方法，称为基于合作边缘的联邦平均（CE-FedAvg），其中每个边缘服务器既协调其自身覆盖范围内的设备之间的协作模型训练，又与其他边缘服务器合作，通过分散的共识来学习共享的全局模型。基于基准数据集的实验结果表明，CFEL可以大大减少训练时间，以达到目标模型的精度相比，以前的FL框架。
Federated learning (FL) enables collaborative model training without centralizing data. However, the traditional FL framework is cloud-based and suffers from high communication latency. On the other hand, the edge-based FL framework that relies on an edge server co-located with mobile base station for model aggregation has low communication latency but suffers from degraded model accuracy due to the limited coverage of edge server. In light of high-accuracy but high-latency cloud-based FL and low-latency but low-accuracy edge-based FL, this paper proposes a new FL framework based on cooperative mobile edge networking called cooperative federated edge learning (CFEL) to enable both high-accuracy and low-latency distributed intelligence at mobile edge networks. Considering the unique two-tier network architecture of CFEL, a novel federated optimization method dubbed cooperative edge-based federated averaging (CE-FedAvg) is further developed, wherein each edge server both coordinates collaborative model training among the devices within its own coverage and cooperates with other edge servers to learn a shared global model through decentralized consensus. Experimental results based on benchmark datasets show that CFEL can largely reduce the training time to achieve a target model accuracy compared with prior FL frameworks.