发表机构
Beijing University of Posts and Telecommunications; Jiaxing University; Northwestern Polytechnical University; Southeast University（北京邮电大学; 嘉兴学院; 西北工业大学; 东南大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对无线联邦学习中的数据异构和不可靠传输问题，提出FedRW框架，联合优化学习、路径选择和传输参数，实现更高精度和更快收敛。
AI 中文摘要
在无线联邦学习（FL）中，数据异构性和多次本地更新会导致客户端漂移，从而降低模型收敛性能。此外，不可靠的无线链路会进一步影响训练，因为传输错误可能使模型更新失效。为了解决这些挑战，我们提出了联邦随机游走平均（FedRW）框架，它是联邦平均（FedAvg）的一种变体，通过沿随机游走（RW）路径更新模型并在服务器处聚合来缓解数据异构性。模型参数以数据包形式传输，并支持重传，以通过减轻RW路径上的无线错误来提高训练质量。同时，无线传输延迟阻碍了FedRW的探索。为此，我们构建了一个联合优化问题，该问题整合了学习、RW路径选择和传输参数调整，旨在在延迟约束下最小化训练损失。通过推导FedRW在不可靠无线网络上的期望收敛上界，我们将问题简化为与任务类型和模型架构无关的一般形式。随后提出了一种分布式解决方案，其中服务器或客户端在本地优化数据包大小和最大重传次数，并通过具有动态剪枝的弹性感知波束搜索高效地选择可靠且可扩展的下一跳节点。仿真结果表明，在高数据异构性下，FedRW相比最先进的基线实现了2.26%-9%的更高准确率。此外，联合优化的FedRW相比基线至少实现了2.78%的更高准确率和更快的收敛速度。
英文摘要
In wireless federated learning (FL), data heterogeneity and multiple local updates induce client drift, degrading model convergence. It is further affected by unreliable wireless links, as transmission errors may invalidate model updates. To address these challenges, we propose a federated random walk averaging (FedRW) framework, which is a variant of federated averaging (FedAvg) that mitigates data heterogeneity by updating models along random walk (RW) paths and aggregating them at the server. Model parameters are transmitted in packets with retransmission support to improve training quality by mitigating wireless errors along RW paths. Meanwhile, wireless transmission delays hinder the exploration of FedRW. To this end, we formulate a joint optimization problem that integrates learning, RW path selection, and transmission parameter tuning, aiming to minimize the training loss under delay constraints. By deriving an upper bound on the expected convergence of FedRW over unreliable wireless networks, we reduce the problem to a general form agnostic to task type and model architecture. A distributed solution is then proposed, in which the server or clients optimize packet size and maximum number of retransmissions locally, and efficiently select reliable and expandable next-hop nodes via a resilience-aware beam search with dynamic pruning. Simulation results show that FedRW achieves 2.26%-9% higher accuracy than state-of-the-art baselines under high data heterogeneity. Furthermore, the jointly optimized FedRW yields at least 2.78% higher accuracy and faster convergence compared to baselines.
