Position-Invariant Graph Convolutional Recurrent Network for Traffic Forecasting
- 27 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (12) , 22497-22511
Abstract
Traffic forecasting leverages multivariate time series analysis to predict traffic patterns. Real-world traffic data comprises two distinct types of latent time-series signals: diffuse signals, which refer to time-varying information propagated across the traffic network, and intrinsic signals, which capture unique, location-specific patterns. However, existing approaches often treat traffic signals solely as diffusion outcomes, overlooking the intrinsic characteristics that can significantly influence model performance. To address this issue, we propose the Position-invariant Graph Convolutional Recurrent Network (PGCRN), which decouples diffuse and intrinsic signals for improved traffic forecasting. Instead of relying on a predefined graph, PGCRN learns graph structures from spatio-temporal data through a learnable position-invariant node representation that forms an adaptive adjacency matrix. This is integrated into a Graph Convolutional Recurrent Network (GCRN) encoder–decoder to jointly capture spatial and temporal dependencies. Furthermore, we introduce a contrastive learning framework in which a node’s time-varying and position-invariant representations form positive pairs, while position-invariant representations from different nodes form negative pairs. The model is trained with a triplet loss. Experiments on four benchmark datasets show that PGCRN consistently outperforms strong baselines. Owing to its computational efficiency, PGCRN is also well suited for deployment on resource-constrained edge devices.Keywords
Funding Information
- National Key Research and Development Program of China (2022YFC3302600)
- Shanghai Technical Service Center of Science and Engineering Computing, Shanghai University
This publication has 35 references indexed in Scilit:
- Illumination Enlightened Spatial-temporal Inconsistency for Deepfake Video Detection2024
- Learning Time-Aware Graph Structures for Spatially Correlated Time Series Forecasting2024
- Multimodal spatio-temporal framework for real-world affect recognitionInternational Journal of Intelligent Networks, 2024
- Dynamic Hypergraph Structure Learning for Traffic Flow Forecasting2023
- Collaborative representation learning for nodes and relations via heterogeneous graph neural networkKnowledge-Based Systems, 2022
- Chiller faults detection and diagnosis with sensor network and adaptive 1D CNNDigital Communications and Networks, 2022
- Blockchain-Based Dynamic Key Management for Heterogeneous Intelligent Transportation SystemsIEEE Internet of Things Journal, 2017
- Long short-term memory neural network for traffic speed prediction using remote microwave sensor dataTransportation Research Part C: Emerging Technologies, 2015
- The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domainsIEEE Signal Processing Magazine, 2013
- Utilizing Real-World Transportation Data for Accurate Traffic Prediction2012