解决无线网络中分布式联邦学习的模型偏差与延迟问题
Asynchronous Decentralized Federated Learning over Lossy Wireless Links via Reception- and Age-Aware Aggregation
- 基于接收状态和信息年龄加权聚合，动态调整节点贡献权重
- 在不同丢包率下性能优于现有方法，误差降低15%以上
- 适合物联网、无人机群等异步无线协同场景
去中心化联邦学习（DFL）使无线边缘节点（如物联网设备、自动驾驶汽车、无人机群、卫星星座）能够协作训练模型。在受限且丢包率高的无线链路下，系统无法依赖重传，模型参数只能以部分片段形式接收，导致两大失效模式：选择偏差（差链路持续被低估）和更新过时（异步节点贡献旧模型）。本文证明经典随机通信会引入与链路丢包率成正比的不可消除选择偏差。提出 DFL-AA（自适应年龄加权聚合的去中心化联邦学习），通过在线信道估计结合逆概率加权（IPW）修正选择偏差，并利用信息年龄（AoI）衰减机制缓解过时问题，无需全局时钟。理论证明其可消除链路质量失真，且在固定有向拓扑下，于不同丢包率和异构信道条件下均持续优于当前最优基线。
原文摘要 · Abstract (English)
Decentralized Federated Learning(DFL) enables collaborative model training across wireless edge nodes, including IoT deployments, autonomous vehicles, UAV swarms, and satellite constellations. Operating over lossy wireless links under constraints, these systems cannot rely on retransmissions, so model parameters must be accepted as partial chunks, leading to two key failure modes, which are selection bias, where poor-quality links are systematically under-represented in gossip aggregation, and update staleness, where asynchronous nodes contribute outdated models. We prove that classical gossip aggregation introduces irreducible selection bias proportional to the link-loss rate. We propose DFL-AA (Decentralized Federated Learning with Adaptive AoI-weighted Aggregation), which corrects selection bias using Inverse Probability Weighting (IPW) with online channel estimation and mitigates staleness via Age-of-Information (AoI) decay without requiring a global clock. We prove that DFL-AA removes link-quality distortion in expectation and consistently outperforms state-of-the-art baselines across varying loss rates and heterogeneous channel conditions on fixed directed topologies.
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。