Papers › Spatio-Temporal Graph Mixformer for Traffic Forecasting

Spatio-Temporal Graph Mixformer for Traffic Forecasting

15 Oct 2023Expert Systems with Applications 2023 10archive 2025-07-28

Mourad Lablack, Yanming Shen

Traffic forecasting is of great importance for intelligent transportation systems (ITS). Because of the intricacy implied in traffic behavior and the non-Euclidean nature of traffic data, it is challenging to give an accurate traffic prediction. Despite that previous studies considered the relationship between different nodes, the majority have relied on a static representation and failed to capture the dynamic node interactions over time. Additionally, prior studies employed RNN-based models to capture the temporal dependency. While RNNs are a popular choice for forecasting problems, they tend to be memory hungry and slow to train. Furthermore, recent studies start utilizing similarity algorithms to better express the implication of a node over the other. However, to our knowledge, none have explored the contribution of node 𝑖’s past, over the future state of node 𝑗. In this paper, we propose a Spatio-Temporal Graph Mixformer (STGM) network, a highly optimized model with low memory footprint. We address the aforementioned limits by utilizing a novel attention mechanism to capture the correlation between temporal and spatial dependencies. Specifically, we use convolution layers with a variable field of view for each head to capture long–short term temporal dependency. Additionally, we train an estimator model that express the contribution of a node over the desired prediction. The estimation is fed alongside a distance matrix to the attention mechanism. Meanwhile, we use a gated mechanism and a mixer layer to further select and incorporate the different perspectives. Extensive experiments show that the proposed model enjoys a performance gain compared to the baselines while maintaining the lowest parameter counts.

Paper PDF Code

Code

Mouradost/STGM officialpytorch 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

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Traffic Prediction	METR-LA	STGM	12 steps MAE	3.229	#3 of 20	Archive leaderboard	report
Traffic Prediction	METR-LA	STGM	12 steps MAPE	9.39	#3 of 20	Archive leaderboard	report
Traffic Prediction	METR-LA	STGM	12 steps RMSE	7.099	#3 of 20	Archive leaderboard	report
Traffic Prediction	METR-LA	STGM	MAE @ 12 step	3.229	#3 of 20	Archive leaderboard	report
Traffic Prediction	PEMS-BAY	STGM	MAE @ 12 step	1.857	#6 of 16	Archive leaderboard	report
Traffic Prediction	PEMS-BAY	STGM	RMSE	4.369	#6 of 16	Archive leaderboard	report
Traffic Prediction	PeMSD7(M)	STGM	12 steps MAE	3.002	#7 of 7	Archive leaderboard	report
Traffic Prediction	PeMSD7(M)	STGM	12 steps MAPE	8.01	#7 of 7	Archive leaderboard	report
Traffic Prediction	PeMSD7(M)	STGM	12 steps RMSE	6.331	#7 of 7	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

Absolute Position Encodings Adam Attention BPE Convolution Dense Connections Dilated Convolution Dropout Graph Transformer Label Smoothing Layer Normalization Linear Layer Mixer Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer

1 archive method tag without a method page not shown.

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