BIPPO:面向高能效联邦学习服务的预算感知独立近端策略优化算法
BIPPO: Budget-Aware Independent PPO for Energy-Efficient Federated Learning Services
AI总结:
针对联邦学习客户端选择未考虑能效的问题,提出BIPPO算法,在高度预算受限的非IID数据场景下,其性能优于非RL机制、传统PPO及IPPO,且预算消耗稳定,为IoT-FL提供了优质客户端选择方案。
摘要:
联邦学习(FL)是一种适用于大规模物联网(IoT)系统的有前景的机器学习解决方案,可保证负载分配与隐私保护。但FL本身未考虑基础设施效率,而这是资源受限环境中运行的系统的关键关注点。若干基于强化学习(RL)的解决方案可改进FL的客户端选择,不过它们未考虑资源限制、设备 churn(设备流失)等基础设施挑战。此外,RL方法的训练通常并非为实际应用设计,因为这些方法常未考虑泛化性,也未针对能效进行优化。为填补这一空白,我们提出BIPPO(Budget-aware Independent Proximal Policy Optimization,预算感知独立近端策略优化算法),它是一种高能效多智能体RL解决方案,可提升性能。我们在两种图像分类任务上评估BIPPO,这些任务在高度预算受限的环境中运行,FL客户端针对非独立同分布(non-IID)数据进行训练,这是普通FL面临的具有挑战性的场景。BIPPO的改进采样器使其与非RL机制、传统PPO及IPPO相比,平均准确率得以提升。此外,BIPPO仅消耗可忽略不计的预算比例,即便客户端数量增加,该比例仍保持稳定。总体而言,BIPPO为物联网联邦学习(IoT-FL)中的客户端选择提供了高性能、稳定、可扩展且可持续的解决方案。
英文摘要:
Federated Learning (FL) is a promising machine learning solution in large-scale IoT systems, guaranteeing load distribution and privacy. However, FL does not natively consider infrastructure efficiency, a critical concern for systems operating in resource-constrained environments. Several Reinforcement Learning (RL) based solutions offer improved client selection for FL; however, they do not consider infrastructure challenges, such as resource limitations and device churn. Furthermore, the training of RL methods is often not designed for practical application, as these approaches frequently do not consider generalizability and are not optimized for energy efficiency. To fill this gap, we propose BIPPO (Budget-aware Independent Proximal Policy Optimization), which is an energy-efficient multi-agent RL solution that improves performance. We evaluate BIPPO on two image classification tasks run in a highly budget-constrained setting, with FL clients training on non-IID data, a challenging context for vanilla FL. The improved sampler of BIPPO enables it to increase the mean accuracy compared to non-RL mechanisms, traditional PPO, and IPPO. In addition, BIPPO only consumes a negligible proportion of the budget, which stays consistent even if the number of clients increases. Overall, BIPPO delivers a performant, stable, scalable, and sustainable solution for client selection in IoT-FL.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。