Papers › Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting

Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting

15 Dec 2020arXiv:2012.09641archive 2025-07-28

Mengzhang Li, Zhanxing Zhu

Spatial-temporal data forecasting of traffic flow is a challenging task because of complicated spatial dependencies and dynamical trends of temporal pattern between different roads. Existing frameworks typically utilize given spatial adjacency graph and sophisticated mechanisms for modeling spatial and temporal correlations. However, limited representations of given spatial graph structure with incomplete adjacent connections may restrict effective spatial-temporal dependencies learning of those models. To overcome those limitations, our paper proposes Spatial-Temporal Fusion Graph Neural Networks (STFGNN) for traffic flow forecasting. SFTGNN could effectively learn hidden spatial-temporal dependencies by a novel fusion operation of various spatial and temporal graphs, which is generated by a data-driven method. Meanwhile, by integrating this fusion graph module and a novel gated convolution module into a unified layer, SFTGNN could handle long sequences. Experimental results on several public traffic datasets demonstrate that our method achieves state-of-the-art performance consistently than other baselines.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

MengzhangLI/STFGNN officialmentioned in papermentioned on GitHubmxnet report
lwm412/STFGNN-Pytorch mentioned on GitHubpytorch 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

Traffic Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Traffic Prediction BJTaxi STFGNN MAE @ in 13.83 #4 of 5 Archive leaderboard report
Traffic Prediction BJTaxi STFGNN MAE @ out 13.89 #4 of 5 Archive leaderboard report
Traffic Prediction BJTaxi STFGNN MAPE (%) @ in 19.29 #4 of 5 Archive leaderboard report
Traffic Prediction BJTaxi STFGNN MAPE (%) @ out 19.41 #4 of 5 Archive leaderboard report
Traffic Prediction NYCBike1 STFGNN MAE @ in 6.53 #4 of 4 Archive leaderboard report
Traffic Prediction NYCBike1 STFGNN MAE @ out 6.79 #4 of 4 Archive leaderboard report
Traffic Prediction NYCBike1 STFGNN MAPE (%) @ in 32.14 #4 of 4 Archive leaderboard report
Traffic Prediction NYCBike1 STFGNN MAPE (%) @ out 32.88 #4 of 4 Archive leaderboard report
Traffic Prediction NYCBike2 STFGNN MAE @ in 5.80 #4 of 4 Archive leaderboard report
Traffic Prediction NYCBike2 STFGNN MAE @ out 5.51 #4 of 4 Archive leaderboard report
Traffic Prediction NYCBike2 STFGNN MAPE (%) @ in 30.73 #4 of 4 Archive leaderboard report
Traffic Prediction NYCBike2 STFGNN MAPE (%) @ out 29.98 #4 of 4 Archive leaderboard report
Traffic Prediction NYCTaxi STFGNN MAE @ in 16.25 #4 of 5 Archive leaderboard report
Traffic Prediction NYCTaxi STFGNN MAE @ out 12.47 #4 of 5 Archive leaderboard report
Traffic Prediction NYCTaxi STFGNN MAPE (%) @ in 24.01 #4 of 5 Archive leaderboard report
Traffic Prediction NYCTaxi STFGNN MAPE (%) @ out 23.28 #4 of 5 Archive leaderboard report
Traffic Prediction PeMS07 STFGNN MAE@1h 22.07 #13 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

1x1 ConvolutionConvolutionGated ConvolutionGated Linear Unit

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