arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.00008cs.LGcs.AI
收藏

一种轻量级的高精度时空流量预测方法Transformer

A Lightweight and Accurate Spatial-Temporal Transformer for Traffic Forecasting

The Hong Kong University of Science and Technology(香港科技大学);Chongqing University(重庆大学);National Chung Hsing University(国立中兴大学);National Yang Ming Chiao Tung University(国立阳明交通大学)

Guanyao Li, Shuhan Zhong, S. -H. Gary Chan, Ruiyuan Li, Chih-Chieh Hung, Wen-Chih Peng

摘要:

我们研究的预测问题的交通动态,可能周期性,和联合时空依赖区域之间。给定从时隙0到t-1的城市中各区域的总流入和流出流量,我们预测任意区域在时间t的流量。该领域的现有技术通常以解耦的方式考虑空间和时间依赖性,或者在训练中计算密集,需要调整大量的超参数。我们提出了ST-TIS,一种新的,轻量级的,准确的时空Transformer与信息融合和区域采样的交通预测。ST-TIS通过信息融合和区域采样扩展了经典的Transformer。信息融合模块捕获区域之间复杂的时空依赖性。区域采样模块用于提高效率和预测精度,将依赖学习的计算复杂度从$O(n^2)$降低到$O(n\sqrt{n})$,其中n是区域的数量。由于参数比最先进的模型少得多,我们模型的离线训练在调整和计算方面明显更快(训练时间和网络参数减少了$90\%$)。尽管有这样的训练效率,大量的实验表明,ST-TIS在在线预测中比最先进的方法准确得多(在RMSE上平均提高到$9.5\%$,在MAPE上平均提高到$12.4\%$)。

英文摘要:

We study the forecasting problem for traffic with dynamic, possibly periodical, and joint spatial-temporal dependency between regions. Given the aggregated inflow and outflow traffic of regions in a city from time slots 0 to t-1, we predict the traffic at time t at any region. Prior arts in the area often consider the spatial and temporal dependencies in a decoupled manner or are rather computationally intensive in training with a large number of hyper-parameters to tune. We propose ST-TIS, a novel, lightweight, and accurate Spatial-Temporal Transformer with information fusion and region sampling for traffic forecasting. ST-TIS extends the canonical Transformer with information fusion and region sampling. The information fusion module captures the complex spatial-temporal dependency between regions. The region sampling module is to improve the efficiency and prediction accuracy, cutting the computation complexity for dependency learning from $O(n^2)$ to $O(n\sqrt{n})$, where n is the number of regions. With far fewer parameters than state-of-the-art models, the offline training of our model is significantly faster in terms of tuning and computation (with a reduction of up to $90\%$ on training time and network parameters). Notwithstanding such training efficiency, extensive experiments show that ST-TIS is substantially more accurate in online prediction than state-of-the-art approaches (with an average improvement of up to $9.5\%$ on RMSE, and $12.4\%$ on MAPE).

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。

↑