Runfei Chen developed PASTN, a lightweight model for large-scale traffic prediction
The model uses positional-aware embeddings and temporal attention to improve node distinction and long-range perception
PASTN effectively handles spatiotemporal complexities across various geographical scales
The research has been accepted for presentation at the 104th Transportation Research Board Annual Meeting
📖 Full Retelling
Computer science researcher Runfei Chen introduced a lightweight Positional-aware Spatio-Temporal Network (PASTN) for large-scale traffic prediction in a paper submitted to arXiv on February 25, 2026, addressing the challenge of modeling complex traffic flows across broad geographical areas and extended time periods where existing models struggle with data size limitations and lack of node distinction. The PASTN model introduces innovative positional-aware embeddings to separate each node's representation while utilizing a temporal attention module to improve long-range perception capabilities, enabling the network to effectively capture both temporal and spatial complexities in an end-to-end manner. This approach addresses a critical gap in previous research that had paid less attention to distinguishing individual nodes while maintaining a holistic view of historical data patterns, particularly important as traffic flow forecasting becomes increasingly vital for urban planning and daily transportation logistics in our rapidly urbanizing world.
Data efficiency refers to efficiency of the many processes that can be applied to data such as storage, access, filtering, sharing, etc., and whether or not the processes lead to the desired outcome within resource constraints.
A management definition of data efficiency would be the measure of how d...
Study of algorithms that improve automatically through experience
Machine learning (ML) is a field of study in artificial intelligence concerned with the development and study of statistical algorithms that can learn from data and generalize to unseen data, and thus perform tasks without explicit instructions. Within a subdiscipline in machine learning, advances i...
--> Computer Science > Machine Learning arXiv:2602.22274 [Submitted on 25 Feb 2026] Title: Positional-aware Spatio-Temporal Network for Large-Scale Traffic Prediction Authors: Runfei Chen View a PDF of the paper titled Positional-aware Spatio-Temporal Network for Large-Scale Traffic Prediction, by Runfei Chen View PDF HTML Abstract: Traffic flow forecasting has emerged as an indispensable mission for daily life, which is required to utilize the spatiotemporal relationship between each location within a time period under a graph structure to predict future flow. However, the large travel demand for broader geographical areas and longer time spans requires models to distinguish each node clearly and possess a holistic view of the history, which has been paid less attention to in prior works. Furthermore, increasing sizes of data hinder the deployment of most models in real application environments. To this end, in this paper, we propose a lightweight Positional-aware Spatio-Temporal Network to effectively capture both temporal and spatial complexities in an end-to-end manner. PASTN introduces positional-aware embeddings to separate each node's representation, while also utilizing a temporal attention module to improve the long-range perception of current models. Extensive experiments verify the effectiveness and efficiency of PASTN across datasets of various scales (county, megalopolis and state). Further analysis demonstrates the efficacy of newly introduced modules either. Comments: Accepted for the 104th Transportation Research Board Annual Meeting in 2025 Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2602.22274 [cs.LG] (or arXiv:2602.22274v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2602.22274 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Runfei Chen [ view email ] [v1] Wed, 25 Feb 2026 09:39:17 UTC (355 KB) Full-text links: Access Paper: View a PDF of the paper titled Positional-awa...
