arXiv 2307.025072023-12-17cs.LGcs.AI

STS-CCL：用于城市交通预测的时空同步上下文对比学习

STS-CCL: Spatial-Temporal Synchronous Contextual Contrastive Learning for Urban Traffic Forecasting

Zhejiang University（浙江大学）；South China University of Technology（华南理工大学）；The University of Sydney（悉尼大学）；Chongqing University（重庆大学）；Zhejiang Institute of Industry and Information Technology（浙江工业信息技术研究院）

Lincan Li, Kaixiang Yang, Fengji Luo, Jichao Bi

备注：: This work was accepted by the 49th IEEE International Conference on Acoustics, Speech, & Signal Processing (ICASSP 2024). We will present our work in Seoul, Korea

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出 STS-CCL 城市交通预测模型，通过自适应图增强、时空同步图级对比、语义上下文节点级对比及困难跨视图训练，提升少量标注条件下的大规模时空预测性能。

摘要：

从大规模无标签交通数据中高效捕获复杂的时空表示仍然是一项具有挑战性的任务。针对这一困境，本研究采用先进的对比学习方法，提出了一种新颖的时空同步上下文对比学习（Spatial-Temporal Synchronous Contextual Contrastive Learning，STS-CCL）模型。首先，我们详细阐述了面向时空图数据的基础增强方法和强增强方法；这些方法不仅从图结构和时间特征方面对数据进行扰动，还采用基于学习的动态图视图生成器实现自适应增强。其次，我们引入时空同步对比模块（Spatial-Temporal Synchronous Contrastive Module，STS-CM），以同时捕获良好的时空依赖关系并实现图级对比。为了在负样本过滤中进一步区分节点个体，我们基于语义特征和空间异质性设计了语义上下文对比方法，在实现节点级对比学习的同时完成负样本过滤。最后，我们提出了困难跨视图对比训练方案，并将经典对比损失扩展为一个集成目标函数，从而获得更好的性能。大量实验和评估表明，在 STS-CCL 对比学习模型之上构建预测器，能够取得优于现有交通预测基准的性能。所提出的 STS-CCL 非常适合仅有少量标注数据的大型数据集，以及其他存在数据稀缺问题的时空任务。

英文摘要：

Efficiently capturing the complex spatiotemporal representations from large-scale unlabeled traffic data remains to be a challenging task. In considering of the dilemma, this work employs the advanced contrastive learning and proposes a novel Spatial-Temporal Synchronous Contextual Contrastive Learning (STS-CCL) model. First, we elaborate the basic and strong augmentation methods for spatiotemporal graph data, which not only perturb the data in terms of graph structure and temporal characteristics, but also employ a learning-based dynamic graph view generator for adaptive augmentation. Second, we introduce a Spatial-Temporal Synchronous Contrastive Module (STS-CM) to simultaneously capture the decent spatial-temporal dependencies and realize graph-level contrasting. To further discriminate node individuals in negative filtering, a Semantic Contextual Contrastive method is designed based on semantic features and spatial heterogeneity, achieving node-level contrastive learning along with negative filtering. Finally, we present a hard mutual-view contrastive training scheme and extend the classic contrastive loss to an integrated objective function, yielding better performance. Extensive experiments and evaluations demonstrate that building a predictor upon STS-CCL contrastive learning model gains superior performance than existing traffic forecasting benchmarks. The proposed STS-CCL is highly suitable for large datasets with only a few labeled data and other spatiotemporal tasks with data scarcity issue.

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。