优化多跳网络中无线联邦学习的延迟，实现节点与路由协同调度。
Latency Optimization for Wireless Federated Learning in Multihop Networks
- 提出个性化自适应聚合框架，平衡个体与全局学习目标。
- 联合优化节点与路由，延迟降低最高达69.37%。
- 适用于资源受限、数据异构的分布式智能系统。
本文研究无线联邦学习在多跳网络中的新型延迟最小化问题。系统包含多条路径，每条路径由叶节点和中继节点组成，用于联邦学习模型训练。我们提出一种个性化学习与自适应聚合感知的联邦学习框架（PAFL），通过协调个体与集体学习目标，有效缓解参与节点间的数据异构性。构建了联合优化叶节点、中继节点及中继路由指示器以最小化系统延迟的优化问题，并为中继节点引入能量采集机制以支持其转发任务。该问题计算复杂度高，因此设计了一种基于块坐标下降与逐次凸逼近（SCA）的高效算法。仿真结果表明，所提联合优化方法显著降低延迟，相比仅优化单一节点类型、传统贪婪算法及无路由指示的方案，延迟最多减少69.37%。
原文摘要 · Abstract (English)
In this paper, we study a novel latency minimization problem in wireless federated learning (FL) across multi-hop networks. The system comprises multiple routes, each integrating leaf and relay nodes for FL model training. We explore a personalized learning and adaptive aggregation-aware FL (PAFL) framework that effectively addresses data heterogeneity across participating nodes by harmonizing individual and collective learning objectives. We formulate an optimization problem aimed at minimizing system latency through the joint optimization of leaf and relay nodes, as well as relay routing indicator. We also incorporate an additional energy harvesting scheme for the relay nodes to help with their relay tasks. This formulation presents a computationally demanding challenge, and thus we develop a simple yet efficient algorithm based on block coordinate descent and successive convex approximation (SCA) techniques. Simulation results illustrate the efficacy of our proposed joint optimization approach for leaf and relay nodes with relay routing indicator. We observe significant latency savings in the wireless multi-hop PAFL system, with reductions of up to 69.37% compared to schemes optimizing only one node type, traditional greedy algorithm, and scheme without relay routing indicator.
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。