Spatio-Temporal Graph Structure Learning for Traffic Forecasting

By Qi Zhang, Jianlong Chang, Gaofeng Meng, Shiming Xiang, Chunhong Pan. AAAI Conference on Artificial Intelligence, 2020

301 citations recorded by the source corpus.

As an indispensable part in Intelligent Traffic System (ITS), the task of traffic forecasting inherently subjects to the following three challenging aspects. First, traffic data are physically associated with road networks, and thus should be formatted as traffic graphs rather than regular grid-like tensors. Second, traffic data render strong spatial dependence, which implies that the nodes in the traffic graphs usually have complex and dynamic relationships between each other. Third, traffic data demonstrate strong temporal dependence, which is crucial for traffic time series modeling. To address these issues, we propose a novel framework named Structure Learning Convolution (SLC) that enables to extend the traditional convolutional neural network (CNN) to graph domains and learn the graph structure for traffic forecasting. Technically, SLC explicitly models the structure information into the convolutional operation. Under this framework, various non-Euclidean CNN methods can be considered as particular instances of our formulation, yielding a flexible mechanism for learning on the graph. Along this technical line, two SLC modules are proposed to capture the global and local structures respectively and they are integrated to construct an end-to-end network for traffic forecasting. Additionally, in this process, Pseudo three Dimensional convolution (P3D) networks are combined with SLC to capture the temporal dependencies in traffic data. Extensively comparative experiments on six real-world datasets demonstrate our proposed approach significantly outperforms the state-of-the-art ones.

Subfields: Building and Construction, Transportation

View Paper: https://www.semanticscholar.org/paper/98f2105a2c3a2ab65070296cca8fdbda2aa61694

How researchers see this paper

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

In Building and Construction

1. Junbo Zhang
2. Yu Zheng
3. Yuxuan Liang
4. Zezhi Shao
5. Fei Wang
6. Zhao Zhang
7. Yongjun Xu
8. Guangyin Jin

In Transportation

1. Junbo Zhang
2. Yu Zheng
3. Wei Wei
4. Yuxuan Liang
5. Depeng Jin
6. Zezhi Shao
7. Fei Wang
8. Zhao Zhang

Citations in the corpus

• Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey (2023, background): “Feature initialization-based adaptive graph learning methods perform adaptive graph structure learning based on the given inputs or the hidden states [82], [113], [121], [127], [174]–[177].”
• Spatio-Temporal Meta-Graph Learning for Traffic Forecasting (2022, unknown): “The other GSL strategy, momentary graph (Zhang et al. 2020) (in Figure 1), can be defined in a similar fashion with input signal X t or hidden state H t .”
• Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting (2022, background): “For example, many variants of GCNs, such as GAT [34], MixHop [1], and SGC [38], are adapted to STGNNs for better performance [6, 27, 29, 39, 43, 49].”
• Graph Neural Network for Traffic Forecasting: A Survey (2021, unknown): “Problem Relevant Studies Road Traffic Flow [20], [21], [22], [23], [24], [25], [26], [27], [28], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47], [48], [49], [50], [51], [52], [53], [54], [55], [56], [57], [58], [59], [60], [61], [62],”
• Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution (2021, methodology): “CNN [32] has been proved to be effective and efficient to capture temporal correlations in sequential data [6], [12], [14], [16], [17], [19] but the architecture is relatively more solid and there is little room for adjustment to adapt different situations.”
• Spatio-Temporal Adaptive Embedding Makes Vanilla Transformer SOTA for Traffic Forecasting (2023, background): “Researchers 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 othe”