arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.06255cs.LGcs.AI
收藏

基于标签分解的渐进式监督:一种长期大规模无线流量预测方法

Progressive Supervision via Label Decomposition: An Long-Term and Large-Scale Wireless Traffic Forecasting Method

Shandong University(山东大学)

Daojun Liang, Haixia Zhang, Dongfeng Yuan

AI总结:

针对长期大规模无线流量预测的非平稳性与节点规模挑战,提出基于标签分解的渐进式监督方法PSLD,结合随机子图采样实现高效训练,在三个数据集上性能优于现有最优方法,并开源WTFlib基准库。

摘要:

长期大规模无线流量预测(Long-term and Large-scale Wireless Traffic Forecasting,LL-WTF)对宏观层面的战略性网络管理与综合规划至关重要。然而,由于长期无线流量存在显著的非平稳性,且城市级分布的节点数量庞大,LL-WTF相比短期预测面临更大挑战。为此,我们提出了一种基于标签分解的渐进式监督方法(Progressive Supervision method based on Label Decomposition,PSLD)。具体而言,我们首先提出随机子图采样(Random Subgraph Sampling,RSS)算法,用于从大规模流量数据中采样出可处理的子集,从而实现高效的网络训练。随后,PSLD利用标签分解得到多个易于学习的分量,这些分量在浅层网络中被渐进式学习,并在深层网络中融合,以有效应对LL-WTF任务带来的非平稳性问题。最后,我们在三个大规模无线流量(Wireless Traffic,WT)数据集上将所提方法与多种现有最优(state-of-the-art,SOTA)方法进行对比。大量实验结果表明,所提的PSLD方法性能显著优于现有方法,在三个WT数据集上的性能平均提升幅度分别为2%、4%和11%。此外,我们构建了一个面向无线流量预测的开源库WTFlib以推动相关研究,该库包含众多SOTA方法并提供了强有力的基准。实验可通过https://github.com/Anoise/WTFlib复现。

英文摘要:

Long-term and Large-scale Wireless Traffic Forecasting (LL-WTF) is pivotal for strategic network management and comprehensive planning on a macro scale. However, LL-WTF poses greater challenges than short-term ones due to the pronounced non-stationarity of extended wireless traffic and the vast number of nodes distributed at the city scale. To cope with this, we propose a Progressive Supervision method based on Label Decomposition (PSLD). Specifically, we first introduce a Random Subgraph Sampling (RSS) algorithm designed to sample a tractable subset from large-scale traffic data, thereby enabling efficient network training. Then, PSLD employs label decomposition to obtain multiple easy-to-learn components, which are learned progressively at shallow layers and combined at deep layers to effectively cope with the non-stationary problem raised by LL-WTF tasks. Finally, we compare the proposed method with various state-of-the-art (SOTA) methods on three large-scale WT datasets. Extensive experimental results demonstrate that the proposed PSLD significantly outperforms existing methods, with an average 2%, 4%, and 11% performance improvement on three WT datasets, respectively. In addition, we built an open source library for WT forecasting (WTFlib) to facilitate related research, which contains numerous SOTA methods and provides a strong benchmark.Experiments can be reproduced through https://github.com/Anoise/WTFlib.

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。

↑