Communication-Efficient Online Federated Learning Strategies for Kernel Regression
Communication-Efficient Online Federated Learning Strategies for Kernel Regression
复制标题
DOI：
10.1109/jiot.2022.3218484
复制
发表时间：
2023-03
影响因子：
10.6
通讯作者：
Vinay Chakravarthi Gogineni;Stefan Werner;Yih-Fang Huang;A. Kuh
中科院分区：
文献类型：
--
作者：
Vinay Chakravarthi Gogineni;Stefan Werner;Yih-Fang Huang;A. Kuh
本文介绍了适用于可访问流数据的资源受限设备的联邦学习 (FL) 的高效通信方法。特别是，我们首先提出了一种基于部分共享的在线联邦学习框架（PSO-Fed），其中客户端从数据流中更新本地模型并与服务器交换模型的一小部分，从而减少通信开销。与经典的 FL 方法相比，所提出的策略为不参与全局迭代的客户提供了在新数据到达时更新本地模型的自由。此外，通过设计客户端创新检查，我们还提出了一种事件触发的 PSO-Fed (ETPSO-Fed)，进一步减轻客户端的计算负担，同时提高通信效率。我们在核回归的背景下实现上述框架，其中客户使用基于随机傅里叶特征（RFF）的核最小均方执行本地学习。此外，我们还检查了所提出的 PSO-Fed 的均值和均方收敛性。最后，我们进行实验以确定所提出框架的有效性。我们的结果表明，PSO-Fed 和 ETPSO-Fed 可以与 Online-Fed 竞争，同时需要的通信开销显着减少。模拟表明，与 Online-Fed 相比，PSO-Fed 通信开销减少了 80%，ETPSO-Fed 通信开销减少了 84.5%。值得注意的是，所提出的 PSO-Fed 策略在不涉及额外机制的情况下表现出良好的抵御模型中毒攻击的能力。
This article presents communication-efficient approaches to federated learning (FL) for resource-constrained devices with access to streaming data. In particular, we first propose a partial-sharing-based framework for online federated learning (PSO-Fed), wherein clients update local models from a stream of data and exchange tiny fractions of the model with the server, reducing the communication overhead. In contrast to classical FL approaches, the proposed strategy provides clients who are not part of a global iteration with the freedom to update local models whenever new data arrives. Furthermore, by devising a client-side innovation check, we also propose an event-triggered PSO-Fed (ETPSO-Fed) that further reduces the computational burden of clients while enhancing communication efficiency. We implement the above-mentioned frameworks in the context of kernel regression, where clients perform local learning employing random Fourier features (RFFs)-based kernel least mean squares. In addition, we examine the mean and mean-square convergence of the proposed PSO-Fed. Finally, we conduct experiments to determine the efficacy of the proposed frameworks. Our results show that PSO-Fed and ETPSO-Fed can compete with Online-Fed while requiring significantly less communication overhead. Simulations demonstrate an 80% reduction in PSO-Fed and an 84.5% reduction in ETPSO-Fed communication overhead compared to Online-Fed. Notably, the proposed PSO-Fed strategies show good resilience against model-poisoning attacks without involving additional mechanisms.