arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.11282cs.LG
收藏

面向时空交通预测的视觉语言模型

Vision-LLMs for Spatiotemporal Traffic Forecasting

Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Southwest University(西南大学);Department of Computing and Communication Engineering, Beijing University of Science and Technology(北京科技大学计算机与通信工程学院);Department of Electrical and Computer Engineering, Northwestern University(西北大学电气与计算机工程系)

Ning Yang, Hengyu Zhong, Haijun Zhang, Randall Berry

AI总结:

本文提出ST-Vision-LLM框架,将时空预测转化为视觉-语言融合问题,通过视觉编码器处理历史交通矩阵并结合高效数值编码方案,提升交通预测精度。

摘要:

准确的时空交通预测是密集城市移动网络主动资源管理的关键前提。尽管大型语言模型在时间序列分析中表现出色,但其难以建模基于网格的交通数据的复杂空间依赖性。为解决这一问题,我们提出ST-Vision-LLM,一种将时空预测重新定义为视觉-语言融合问题的新框架。我们的方法利用视觉-语言模型的视觉编码器处理历史全球交通矩阵作为图像序列,为模型提供全面的全局视图以指导单元级预测。为克服大型语言模型处理数值数据的低效性,我们引入了一种高效的编码方案,将浮点值表示为单个标记,结合两阶段数值对齐微调过程。模型首先通过监督微调训练,然后通过组相对策略优化(一种内存高效的强化学习方法)进一步优化预测准确性。在真实世界移动交通数据集上的评估表明,ST-Vision-LLM在长期预测准确性上比现有方法高出15.6%,并在跨领域少样本场景中平均超过最佳基线约30%。我们的广泛实验验证了模型在各种数据稀缺环境中的强大泛化能力。

英文摘要:

Accurate spatiotemporal traffic forecasting is a critical prerequisite for proactive resource management in dense urban mobile networks. While large language models have shown promise in time series analysis, they inherently struggle to model the complex spatial dependencies of grid-based traffic data. Effectively extending large language models to this domain is challenging, as representing the vast amount of information from dense geographical grids can be inefficient and overwhelm the model's context. To address these challenges, we propose ST-Vision-LLM, a novel framework that reframes spatiotemporal forecasting as a vision-language fusion problem. Our approach leverages a Vision-LLM visual encoder to process historical global traffic matrices as image sequences, providing the model with a comprehensive global view to inform cell-level predictions. To overcome the inefficiency of large language models in handling numerical data, we introduce an efficient encoding scheme that represents floating-point values as single tokens via a specialized vocabulary, coupled with a two-stage numerical alignment fine-tuning process. The model is first trained with supervised fine-tuning and then further optimized for predictive accuracy using group relative policy optimization, a memory-efficient reinforcement learning method. Evaluations on real-world mobile traffic datasets demonstrate that ST-Vision-LLM outperforms existing methods by 15.6% in long-term prediction accuracy and exceeds the best baseline by around 30% on average in cross-domain few-shot scenarios. Our extensive experiments validate the model's strong generalization capabilities across various data-scarce environments.

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。

↑