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

TL;DR

This paper introduces STS-CCL, a novel contrastive learning framework that effectively captures complex spatiotemporal features from large-scale unlabeled traffic data, improving urban traffic forecasting accuracy.

Contribution

The work proposes a new contrastive learning model with advanced augmentation, a spatial-temporal synchronous contrastive module, and semantic contextual contrastive methods for better spatiotemporal representation learning.

Findings

Outperforms existing traffic forecasting benchmarks.

Effective on large datasets with limited labeled data.

Enhances spatiotemporal feature extraction for urban traffic prediction.

Abstract

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.