联合优化路由与剪枝，提升带宽受限下联邦学习的通信效率与模型精度。
Joint Routing and Model Pruning for Decentralized Federated Learning in Bandwidth-Constrained Multi-Hop Wireless Networks
- 同时优化数据传输路径和模型剪枝率，降低通信延迟。
- 相比未剪枝系统，传输延迟减少27.8%，测试准确率提升约12%。
- 适用于资源受限的多跳无线联邦学习场景，尤其适合边缘设备部署。
去中心化联邦学习（D-FL）可在无中心服务器情况下实现隐私保护训练，但多跳模型交换与聚合常受通信资源限制。为此，我们提出一种联合路由与剪枝框架，通过优化路由路径和剪枝率，在保证通信延迟不超限的前提下，最小化各客户端模型偏差之和。分析表明，模型偏差总和影响D-FL收敛边界，而各客户端的模型保留率与传输路径相关，因此问题可转化为路由优化。基于此，我们设计了一种低延迟传输路径选择算法，使更多参数在时间预算内完成传输，从而改善模型收敛性。仿真结果表明，相较于未剪枝系统，所提框架平均传输延迟降低27.8%，测试准确率提升约12%；相比标准基准路由算法，准确率提升约8%。
原文摘要 · Abstract (English)
Decentralized federated learning (D-FL) enables privacy-preserving training without a central server, but multi-hop model exchanges and aggregation are often bottlenecked by communication resource constraints. To address this issue, we propose a joint routing-and-pruning framework that optimizes routing paths and pruning rates to maintain communication latency within prescribed limits. We analyze how the sum of model biases across all clients affects the convergence bound of D-FL and formulate an optimization problem that maximizes the model retention rate to minimize these biases under communication constraints. Further analysis reveals that each client's model retention rate is path-dependent, which reduces the original problem to a routing optimization. Leveraging this insight, we develop a routing algorithm that selects latency-efficient transmission paths, allowing more parameters to be delivered within the time budget and thereby improving D-FL convergence. Simulations demonstrate that, compared with unpruned systems, the proposed framework reduces average transmission latency by 27.8% and improves testing accuracy by approximately 12%. Furthermore, relative to standard benchmark routing algorithms, the proposed routing method improves accuracy by roughly 8%.
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。