通过对比预训练在城市交通预测中嵌入空间上下文
Embedding spatial context in urban traffic forecasting with contrastive pre-training
AI总结：
针对城市交通预测缺乏上下文感知方法的问题，提出基于交通商图的几何编码器，结合OpenStreetMap数据经对比预训练后集成到GNN交通预测模型中，无需额外交通数据即可提升泛化性与性能。
摘要：
城市交通预测是一个常见问题，在城市规划、土木工程和交通等领域有着广泛应用。本文研究通过预训练提升交通预测效果，重点关注时空图方法。尽管学界已探索并广泛研究了多种解决交通预测问题的机器学习方法，但仍缺乏更具上下文感知的方法：即研究相关非交通数据如何提升交通预测问题的预测性能，我们将这类数据称为空间上下文。我们提出一种通过交通商图概念结合道路与交通信息的新方法，该商图由道路几何结构和交通传感器构建而成。我们还定义了一种以几何编码器形式编码该关系的方法，该编码器采用对比学习方法预训练，并借助OpenStreetMap数据增强。我们提出并讨论了利用对比预训练范式，将该几何编码器与现有基于图神经网络（GNN）的交通预测模型相集成的方法。我们证明了这种混合模型无需额外交通数据即可提升泛化能力和性能的潜力。本文代码可在https://github.com/mattchrlw/forecasting-on-new-roads获取。
英文摘要：
Urban traffic forecasting is a commonly encountered problem, with wide-ranging applications in fields such as urban planning, civil engineering and transport. In this paper, we study the enhancement of traffic forecasting with pre-training, focusing on spatio-temporal graph methods. While various machine learning methods to solve traffic forecasting problems have been explored and extensively studied, there is a gap of a more contextual approach: studying how relevant non-traffic data can improve prediction performance on traffic forecasting problems. We call this data spatial context. We introduce a novel method of combining road and traffic information through the notion of a traffic quotient graph, a quotient graph formed from road geometry and traffic sensors. We also define a way to encode this relationship in the form of a geometric encoder, pre-trained using contrastive learning methods and enhanced with OpenStreetMap data. We introduce and discuss ways to integrate this geometric encoder with existing graph neural network (GNN)-based traffic forecasting models, using a contrastive pre-training paradigm. We demonstrate the potential for this hybrid model to improve generalisation and performance with zero additional traffic data. Code for this paper is available at https://github.com/mattchrlw/forecasting-on-new-roads.
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。
