arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.00732cs.DC
收藏

面向无线流量预测的梯度压缩与相关性驱动的联邦学习

Gradient Compression and Correlation Driven Federated Learning for Wireless Traffic Prediction

Chuanting Zhang, Haixia Zhang, Shuping Dang, Basem Shihada, Mohamed-Slim Alouini

AI总结:

本文提出一种基于梯度压缩与梯度相关性驱动聚合策略的联邦学习算法,用于无线流量预测,在保持预测精度的同时将通信效率提升最多两个数量级。

摘要:

无线流量预测在蜂窝网络中发挥着不可或缺的作用,能够帮助通信系统实现主动自适应调整。在此方向上,基于联邦学习(Federated Learning, FL)的边缘无线流量预测因无需传输原始数据且能增强隐私保护而受到广泛关注。然而,基于联邦学习的无线流量预测方法仍然依赖本地客户端与服务器之间大量的数据传输来更新本地模型。此外,如何在联邦学习框架下建模本地客户端之间的空间依赖关系仍然是一个尚未明确的问题。为了解决这些问题,我们提出了一种创新的联邦学习算法,该算法采用梯度压缩和相关性驱动技术,在保持预测精度的同时有效降低数据传输负载。我们的方法首先在无线流量预测中引入梯度稀疏化,从而在模型训练过程中实现显著的数据压缩。随后,我们实现误差反馈和梯度跟踪方法,以缓解由压缩引起的性能下降。此外,我们开发了三种基于梯度相关性的定制化模型聚合策略,从而能够捕捉不同客户端之间的空间依赖关系。我们在两个真实世界数据集上进行了实验,结果表明,通过捕捉本地客户端之间的时空特征和相关性,所提算法优于当前最先进的算法,并且在不损失预测精度的前提下,可将通信效率提升最多两个数量级。代码可在 https://github.com/chuanting/FedGCC 获取。

英文摘要:

Wireless traffic prediction plays an indispensable role in cellular networks to achieve proactive adaptation for communication systems. Along this line, Federated Learning (FL)-based wireless traffic prediction at the edge attracts enormous attention because of the exemption from raw data transmission and enhanced privacy protection. However FL-based wireless traffic prediction methods still rely on heavy data transmissions between local clients and the server for local model updates. Besides, how to model the spatial dependencies of local clients under the framework of FL remains uncertain. To tackle this, we propose an innovative FL algorithm that employs gradient compression and correlation-driven techniques, effectively minimizing data transmission load while preserving prediction accuracy. Our approach begins with the introduction of gradient sparsification in wireless traffic prediction, allowing for significant data compression during model training. We then implement error feedback and gradient tracking methods to mitigate any performance degradation resulting from this compression. Moreover, we develop three tailored model aggregation strategies anchored in gradient correlation, enabling the capture of spatial dependencies across diverse clients. Experiments have been done with two real-world datasets and the results demonstrate that by capturing the spatio-temporal characteristics and correlation among local clients, the proposed algorithm outperforms the state-of-the-art algorithms and can increase the communication efficiency by up to two orders of magnitude without losing prediction accuracy. Code is available at https://github.com/chuanting/FedGCC.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑