Papers › Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for...

Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting

3 Apr 2020archive 2025-07-28

Chao Song, Youfang Lin, Shengnan Guo, Huaiyu Wan

Spatial-temporal network data forecasting is of great importance in a huge amount of applications for traffic management and urban planning. However, the underlying complex spatial-temporal correlations and heterogeneities make this problem challenging. Existing methods usually use separate components to capture spatial and temporal correlations and ignore the heterogeneities in spatial-temporal data. In this paper, we propose a novel model, named Spatial-Temporal Synchronous Graph Convolutional Networks (STSGCN), for spatial-temporal network data forecasting. The model is able to effectively capture the complex localized spatial-temporal correlations through an elaborately designed spatial-temporal synchronous modeling mechanism. Meanwhile, multiple modules for different time periods are designed in the model to effectively capture the heterogeneities in localized spatialtemporal graphs. Extensive experiments are conducted on four real-world datasets, which demonstrates that our method achieves the state-of-the-art performance and consistently outperforms other baselines.

PaperPDFCode

Code

Davidham3/STSGCN officialmentioned in papermxnet report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ManagementTraffic Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Traffic Prediction BJTaxi STSGCN MAE @ in 12.72 #3 of 5 Archive leaderboard report
Traffic Prediction BJTaxi STSGCN MAE @ out 12.79 #3 of 5 Archive leaderboard report
Traffic Prediction BJTaxi STSGCN MAPE (%) @ in 17.22 #3 of 5 Archive leaderboard report
Traffic Prediction BJTaxi STSGCN MAPE (%) @ out 17.35 #3 of 5 Archive leaderboard report
Traffic Prediction NYCBike1 STSGCN MAE @ in 5.81 #3 of 4 Archive leaderboard report
Traffic Prediction NYCBike1 STSGCN MAE @ out 6.10 #3 of 4 Archive leaderboard report
Traffic Prediction NYCBike1 STSGCN MAPE (%) @ in 26.51 #3 of 4 Archive leaderboard report
Traffic Prediction NYCBike1 STSGCN MAPE (%) @ out 27.56 #3 of 4 Archive leaderboard report
Traffic Prediction NYCBike2 STSGCN MAE @ in 5.25 #3 of 4 Archive leaderboard report
Traffic Prediction NYCBike2 STSGCN MAE @ out 4.94 #3 of 4 Archive leaderboard report
Traffic Prediction NYCBike2 STSGCN MAPE (%) @ in 29.26 #3 of 4 Archive leaderboard report
Traffic Prediction NYCBike2 STSGCN MAPE (%) @ out 28.02 #3 of 4 Archive leaderboard report
Traffic Prediction NYCTaxi STSGCN MAE @ in 13.69 #3 of 5 Archive leaderboard report
Traffic Prediction NYCTaxi STSGCN MAE @ out 10.75 #3 of 5 Archive leaderboard report
Traffic Prediction NYCTaxi STSGCN MAPE (%) @ in 22.91 #3 of 5 Archive leaderboard report
Traffic Prediction NYCTaxi STSGCN MAPE (%) @ out 22.37 #3 of 5 Archive leaderboard report
Traffic Prediction PeMS07 STSGCN MAE@1h 24.26 #15 of 17 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Graph Convolutional Networks

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections