提出线性复杂度图网络，让大规模交通预测又快又准
GraphSparseNet: a Novel Method for Large Scale Traffic Flow Prediction
- 用特征提取与关系压缩模块，实现线性计算开销
- 相比先进线性模型训练提速3.51倍，精度不降
- 适合超大规模路网实时交通预测场景
交通流预测是智能路径规划与动态交通管理中的关键时空数据挖掘任务。近年来，图神经网络（GNN）通过捕捉复杂的时空动态显著提升了预测精度，但其模型复杂度随图中节点数呈指数增长，限制了可扩展性。现有稀疏化、分解和核方法要么未能彻底解决复杂度问题，要么牺牲预测精度。本文提出GraphSparseNet（GSNet）框架，由特征提取器与关系压缩器两模块构成，均保持线性时间与空间复杂度，整体模型复杂度降至线性级别。在多个真实世界数据集上的实验表明，GSNet相较最先进线性模型训练时间缩短3.51倍，同时保持高预测性能。
原文摘要 · Abstract (English)
Traffic flow forecasting is a critical spatio-temporal data mining task with wide-ranging applications in intelligent route planning and dynamic traffic management. Recent advancements in deep learning, particularly through Graph Neural Networks (GNNs), have significantly enhanced the accuracy of these forecasts by capturing complex spatio-temporal dynamics. However, the scalability of GNNs remains a challenge due to their exponential growth in model complexity with increasing nodes in the graph. Existing methods to address this issue, including sparsification, decomposition, and kernel-based approaches, either do not fully resolve the complexity issue or risk compromising predictive accuracy. This paper introduces GraphSparseNet (GSNet), a novel framework designed to improve both the scalability and accuracy of GNN-based traffic forecasting models. GraphSparseNet is comprised of two core modules: the Feature Extractor and the Relational Compressor. These modules operate with linear time and space complexity, thereby reducing the overall computational complexity of the model to a linear scale. Our extensive experiments on multiple real-world datasets demonstrate that GraphSparseNet not only significantly reduces training time by 3.51x compared to state-of-the-art linear models but also maintains high predictive performance.
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。