Large-Scale Traffic Data Imputation with Spatiotemporal Semantic Understanding

TL;DR

This paper introduces GT-TDI, a novel graph transformer model that leverages semantic information of road networks to improve large-scale traffic data imputation, outperforming existing methods especially in complex missing data scenarios.

Contribution

The study proposes a Graph Transformer model incorporating semantic descriptions for spatiotemporal traffic data imputation, addressing limitations of prior methods that ignore network-wide semantic information.

Findings

GT-TDI outperforms conventional, tensor factorization, and deep learning methods.

The model effectively handles complex missing data patterns.

Semantic information enhances spatiotemporal correlation capture.

Abstract

Large-scale data missing is a challenging problem in Intelligent Transportation Systems (ITS). Many studies have been carried out to impute large-scale traffic data by considering their spatiotemporal correlations at a network level. In existing traffic data imputations, however, rich semantic information of a road network has been largely ignored when capturing network-wide spatiotemporal correlations. This study proposes a Graph Transformer for Traffic Data Imputation (GT-TDI) model to impute large-scale traffic data with spatiotemporal semantic understanding of a road network. Specifically, the proposed model introduces semantic descriptions consisting of network-wide spatial and temporal information of traffic data to help the GT-TDI model capture spatiotemporal correlations at a network level. The proposed model takes incomplete data, the social connectivity of sensors, and semantic descriptions as input to perform imputation tasks with the help of Graph Neural Networks (GNN) and Transformer. On the PeMS freeway dataset, extensive experiments are conducted to compare the proposed GT-TDI model with conventional methods, tensor factorization methods, and deep learning-based methods. The results show that the proposed GT-TDI outperforms existing methods in complex missing patterns and diverse missing rates. The code of the GT-TDI model will be available at https://github.com/KP-Zhang/GT-TDI.