用控制理论动态调控参与率，让联邦学习更省通信和计算。
Controlling Participation in Federated Learning with Feedback
- 基于控制理论设计确定性参与策略，按优化动态调节每客户端参与率。
- 在图像分类任务中，相比随机选参，通信与计算效率提升最高50%。
- 适合追求高效、稳定训练的工业级联邦学习系统使用。
我们解决联邦学习中的客户端参与问题，传统方法通常在每轮训练中随机选取少量客户端。相比之下，我们提出 FedBack，一种基于 ADMM 的联邦学习确定性方法，利用控制理论原理管理客户端参与。FedBack 将客户端参与建模为离散时间动力系统，并采用积分反馈控制器，根据客户端的优化动态个体化调整其参与率。通过借鉴近期联邦学习研究，我们为该方法提供了全局收敛保证。在联邦图像分类上的数值实验表明，与依赖随机客户端选择的算法相比，FedBack 最多可实现 50% 的通信与计算效率提升。
原文摘要 · Abstract (English)
We address the problem of client participation in federated learning, where traditional methods typically rely on a random selection of a small subset of clients for each training round. In contrast, we propose FedBack, a deterministic approach that leverages control-theoretic principles to manage client participation in ADMM-based federated learning. FedBack models client participation as a discrete-time dynamical system and employs an integral feedback controller to adjust each client's participation rate individually, based on the client's optimization dynamics. We provide global convergence guarantees for our approach by building on the recent federated learning research. Numerical experiments on federated image classification demonstrate that FedBack achieves up to 50\% improvement in communication and computational efficiency over algorithms that rely on a random selection of clients.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。