Dynamic Spatial-Temporal Graph Convolutional Neural Networks for Traffic Forecasting

By Zulong Diao, Xin Wang, Dafang Zhang, Yingru Liu, Kun Xie, Shaoyao He. AAAI Conference on Artificial Intelligence, 2019

344 citations recorded by the source corpus.

Graph convolutional neural networks (GCNN) have become an increasingly active field of research. It models the spatial dependencies of nodes in a graph with a pre-defined Laplacian matrix based on node distances. However, in many application scenarios, spatial dependencies change over time, and the use of fixed Laplacian matrix cannot capture the change. To track the spatial dependencies among traffic data, we propose a dynamic spatio-temporal GCNN for accurate traffic forecasting. The core of our deep learning framework is the finding of the change of Laplacian matrix with a dynamic Laplacian matrix estimator. To enable timely learning with a low complexity, we creatively incorporate tensor decomposition into the deep learning framework, where real-time traffic data are decomposed into a global component that is stable and depends on long-term temporal-spatial traffic relationship and a local component that captures the traffic fluctuations. We propose a novel design to estimate the dynamic Laplacian matrix of the graph with above two components based on our theoretical derivation, and introduce our design basis. The forecasting performance is evaluated with two realtime traffic datasets. Experiment results demonstrate that our network can achieve up to 25% accuracy improvement.

Subfields: Building and Construction, Transportation

View Paper: https://www.semanticscholar.org/paper/4b388c9ac1a16f771c33ee08c0c8848ef66d3fb8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Hangchen Liu
Zheng Dong
Jiewen Deng
Jinliang Deng
Quanjun Chen
Xuan Song
Renhe Jiang

Citations in the corpus

Deep Learning for Spatio-Temporal Data Mining: A Survey (2019, unknown): “Application domains Related works Transportation [189], [199], [125], [32], [30], [6], [33], [136], [60], [121], [27], [114], [177], [90], [23], [73], [117], [135], [89], [148], [85], [137], [155], [157], [79], [107], [201], [22], [24], [108], [105], [16], [106], [93], [15], [175], [176], [104], [14”
Spatio-Temporal Meta-Graph Learning for Traffic Forecasting (2022, unknown): “…relationships can be naturally represented by graph and sequence respectively, the mainstream models handle them by leveraging GCN-based modules (Diao et al. 2019; Guo et al. 2019; Geng et al. 2019; Zhang et al. 2021) and sequence models, such as Recurrent Neural Networks (RNNs) (Li et al.…”
Spatio-Temporal Adaptive Embedding Makes Vanilla Transformer SOTA for Traffic Forecasting (2023, background): “…have devoted considerable effort to developing fancy and complicated models for traffic forecasting, such as novel graph convolutions [2, 3, 8–10, 12, 17, 20, 27, 30, 31, 36, 40], learning graph structures [14, 23, 33, 34, 39], efficient attention mechanisms [5, 19, 32, 42, 43], and other…”
Deep Learning on Traffic Prediction: Methods, Analysis, and Future Directions (2021, unknown): “ChebNet CNN (1-D Conv) [51] (2-D Conv) [103] RNN [73], [96], [104], [105] RNN+Attention [75]”