Spatial-Temporal Graph Contrastive Learning with Decreasing Masks for Traffic Flow Forecasting

In recent years, Contrastive learning has shown great potential in traffic flow prediction tasks. However, existing contrastive learning methods have difficulties in dealing with missing data and noise, and it is difficult to fully capture local and global correlations by relying on a single contrast method. In this paper, a Decreasing Mask Spatio-Temporal Graph Comparison Learning Model (DMSTGCL) is proposed. The model dynamically adjusts the mask ratio through the adaptive mask reduction technique to effectively deal with the problem of missing data and noise. Meanwhile, the projection head is further combined with the TripleAttention mechanism in the spatio-temporal contrast learning process, which overcomes the limitations of a single contrast method and captures the complex relationships in local and global space more effectively. Experiments on three real-world datasets demonstrate that DMSTGCL achieves significantly higher prediction accuracy than existing methods.

Authors

• Bin Ren
• Yongfa Zhang
• Yamin Wen
• Haocheng Luo
• Hao Zhang
• Chunhong He

Keywords

• Training
• Adaptation models
• Accuracy
• Noise
• Contrastive learning
• Predictive models
• Graph neural networks
• Spatiotemporal phenomena
• Forecasting
• Intelligent robots
• Traffic Flow
• Self-supervised Learning
• Traffic Flow Forecasting
• Graph Contrastive Learning
• Local Correlation
• Global Correlation
• Global Space
• Traffic Prediction
• Missing Data Problem
• Convolutional Network
• Convolutional Neural Network
• Local Features
• Spatial Features
• Network Topology
• Mean Absolute Error
• Recurrent Neural Network
• Spatial Dimensions
• Noisy Data
• Simple Comparison
• Urban Network
• Global Dependencies
• Traffic Data
• Mean Absolute Percentage Error
• Graph Convolution
• Local Dependence
• Gating Mechanism
• Capture Complex
• Sensor Failure
• Urban Transport
• data augmentation