Federated Learning Over Multihop Wireless Networks With In-Network Aggregation
Federated Learning Over Multihop Wireless Networks With In-Network Aggregation
复制标题
基于网内聚合的多跳无线网络联合学习
DOI：
10.1109/twc.2022.3168538
复制
发表时间：
2022-06
影响因子：
10.4
通讯作者：
Xianhao Chen;Guangyu Zhu;Yiqin Deng;Yuguang Fang
中科院分区：
文献类型：
--
作者：
Xianhao Chen;Guangyu Zhu;Yiqin Deng;Yuguang Fang
边缘的通信限制被广泛认为是联邦学习（FL）的主要瓶颈。多跳无线网络提供了一种具有成本效益的解决方案，可以增强边缘的服务覆盖和频谱效率，这可以促进大规模和高效的机器学习（ML）模型聚合。然而，FL在多跳无线网络很少被研究。在本文中，我们优化FL在无线网状网络考虑到在网状路由器和客户端的通信和计算资源的异构性。我们提出了一个框架，每个中间路由器执行网络模型聚合之前发送数据到下一跳，以减少传出的数据流量，从而聚合更多的模型在有限的通信资源。为了加速模型训练，我们通过联合考虑模型聚合、路由和频谱分配来制定我们的优化问题。虽然问题是一个非凸的混合整数非线性规划，我们把它转化为一个混合整数线性规划（MILP），并开发了一个粗粒度的固定过程，以有效地解决它。仿真结果表明了该方法的有效性，以及网内聚合方案相对于无网内聚合方案的优越性。
Communication limitation at the edge is widely recognized as a major bottleneck for federated learning (FL). Multi-hop wireless networking provides a cost-effective solution to enhance service coverage and spectrum efficiency at the edge, which could facilitate large-scale and efficient machine learning (ML) model aggregation. However, FL over multi-hop wireless networks has rarely been investigated. In this paper, we optimize FL over wireless mesh networks by taking into account the heterogeneity in communication and computing resources at mesh routers and clients. We present a framework that each intermediate router performs in-network model aggregation before sending the data to the next hop, so as to reduce the outgoing data traffic and hence aggregate more models under limited communication resources. To accelerate model training, we formulate our optimization problem by jointly considering model aggregation, routing, and spectrum allocation. Although the problem is a non-convex mixed-integer nonlinear programming, we transform it into a mixed-integer linear programming (MILP), and develop a coarse-grained fixing procedure to solve it efficiently. Simulation results demonstrate the effectiveness of the solution approach, and the superiority of the in-network aggregation scheme over the counterpart without in-network aggregation.