发表机构
University of Zagreb; University of Thessaly; International Hellenic University; University of Glasgow; Trinity College Dublin; Italian National Research Council（萨格勒布大学; 塞萨利大学; 国际希腊大学; 格拉斯哥大学; 都柏林圣三一学院; 意大利国家研究委员会）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种约束贝叶斯优化框架，用于在资源受限的物联网环境中高效配置分层联邦学习，以平衡能耗、执行时间和预测性能，并在植物病害分类任务上仅探索11.11%搜索空间即达到接近最优性能。
AI 中文摘要
在资源受限的物联网环境中部署分层联邦学习（HFL）需要仔细配置，以平衡预测性能与能耗和执行时间。这一挑战在智能农业中尤为突出，因为分布式物联网设备可以在有限的计算和通信资源下支持自动化植物病害分类。本文提出了一种约束贝叶斯优化框架，用于高效配置HFL部署。所提出的方法联合探索深度学习骨干架构、聚合策略和通信轮数，而联邦规模则根据农业部署的空间覆盖要求来确定。加权目标函数捕获用户在能耗、执行时间和预测性能之间的权衡，而显式约束确保符合部署特定的资源和精度要求。该框架在基于物联网的植物病害分类任务上进行了评估，考虑了多种深度学习架构、联邦聚合策略和通信轮设置。30次独立优化运行的实验结果表明，所提出的方法仅探索了搜索空间的11.11%，同时始终识别出在穷举搜索最优解1%范围内的解，平均最优性差距仅为0.056%。
英文摘要
The deployment of Hierarchical Federated Learning (HFL) in resource-constrained Internet of Things (IoT) environments requires careful configuration to balance predictive performance with energy consumption and execution time. This challenge is particularly relevant to smart agriculture, where distributed IoT devices can support automated plant disease classification while operating under limited computational and communication resources. This paper presents a constrained Bayesian Optimization framework for the efficient configuration of HFL deployments. The proposed approach jointly explores the deep learning backbone architecture, aggregation strategy, and number of communication rounds, while the federation size is determined according to the spatial coverage requirements of the agricultural deployment. A weighted objective function captures user-defined trade-offs among energy consumption, execution time, and predictive performance, while explicit constraints ensure compliance with deployment-specific resource and accuracy requirements. The framework is evaluated on an IoT-based plant disease classification task considering multiple deep learning architectures, federated aggregation strategies, and communication-round settings. Experimental results across 30 independent optimization runs show that the proposed approach explores only 11.11% of the search space, while consistently identifying solutions within 1% of the exhaustive-search optimum, with a mean optimality gap of only 0.056%.
CommentsAccepted for publication at Next Generation Communications (NextGCom) conference
