轻量化联邦学习框架，兼顾通信效率与隐私保护。
Lightweight Federated Learning over Wireless Edge Networks
- 融合功率控制、模型剪枝与梯度量化，降低无线边缘计算负担。
- 理论推导收敛误差表达式，实测在延迟和能耗约束下表现更优。
- 适合资源受限的移动设备部署，尤其关注隐私与能效场景。
随着连接无线网络的智能设备激增，数据生成速度迅猛增长，亟需机器学习技术挖掘其价值。然而，集中式机器学习面临通信开销大与隐私泄露风险。联邦学习（FL）为网络边缘提供替代方案，但在无线环境中的实际部署仍具挑战。本文提出一种轻量化联邦学习（LTFL）框架，集成无线传输功率控制、模型剪枝与梯度量化技术。我们推导了考虑传输误差、模型剪枝误差与梯度量化误差的联邦学习收敛差距闭式表达式，并据此构建优化问题，在满足延迟与能量约束条件下最小化收敛差距。为高效求解非凸问题，我们推导出最优模型剪枝率与梯度量化等级的闭式解，并采用贝叶斯优化进行传输功率控制。在真实数据集上的大量实验表明，LTFL优于现有先进方案。
原文摘要 · Abstract (English)
With the exponential growth of smart devices connected to wireless networks, data production is increasing rapidly, requiring machine learning (ML) techniques to unlock its value. However, the centralized ML paradigm raises concerns over communication overhead and privacy. Federated learning (FL) offers an alternative at the network edge, but practical deployment in wireless networks remains challenging. This paper proposes a lightweight FL (LTFL) framework integrating wireless transmission power control, model pruning, and gradient quantization. We derive a closed-form expression of the FL convergence gap, considering transmission error, model pruning error, and gradient quantization error. Based on these insights, we formulate an optimization problem to minimize the convergence gap while meeting delay and energy constraints. To solve the non-convex problem efficiently, we derive closed-form solutions for the optimal model pruning ratio and gradient quantization level, and employ Bayesian optimization for transmission power control. Extensive experiments on real-world datasets show that LTFL outperforms state-of-the-art schemes.
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。