Papers › Spatio-Temporal Self-Supervised Learning for Traffic Flow Prediction

Spatio-Temporal Self-Supervised Learning for Traffic Flow Prediction

7 Dec 2022arXiv:2212.04475archive 2025-07-28

Jiahao Ji, Jingyuan Wang, Chao Huang, Junjie Wu, Boren Xu, Zhenhe Wu, Junbo Zhang, Yu Zheng

Robust prediction of citywide traffic flows at different time periods plays a crucial role in intelligent transportation systems. While previous work has made great efforts to model spatio-temporal correlations, existing methods still suffer from two key limitations: i) Most models collectively predict all regions' flows without accounting for spatial heterogeneity, i.e., different regions may have skewed traffic flow distributions. ii) These models fail to capture the temporal heterogeneity induced by time-varying traffic patterns, as they typically model temporal correlations with a shared parameterized space for all time periods. To tackle these challenges, we propose a novel Spatio-Temporal Self-Supervised Learning (ST-SSL) traffic prediction framework which enhances the traffic pattern representations to be reflective of both spatial and temporal heterogeneity, with auxiliary self-supervised learning paradigms. Specifically, our ST-SSL is built over an integrated module with temporal and spatial convolutions for encoding the information across space and time. To achieve the adaptive spatio-temporal self-supervised learning, our ST-SSL first performs the adaptive augmentation over the traffic flow graph data at both attribute- and structure-levels. On top of the augmented traffic graph, two SSL auxiliary tasks are constructed to supplement the main traffic prediction task with spatial and temporal heterogeneity-aware augmentation. Experiments on four benchmark datasets demonstrate that ST-SSL consistently outperforms various state-of-the-art baselines. Since spatio-temporal heterogeneity widely exists in practical datasets, the proposed framework may also cast light on other spatial-temporal applications. Model implementation is available at https://github.com/Echo-Ji/ST-SSL.

PaperPDFCode

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

Code

echo-ji/st-ssl officialmentioned in paperpytorch 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

AttributePredictionRobust Traffic PredictionSelf-Supervised LearningSpatio-Temporal ForecastingTraffic Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Traffic Prediction BJTaxi ST-SSL MAE @ in 11.31 #1 of 5 Archive leaderboard report
Traffic Prediction BJTaxi ST-SSL MAE @ out 11.4 #1 of 5 Archive leaderboard report
Traffic Prediction BJTaxi ST-SSL MAPE (%) @ in 15.03 #1 of 5 Archive leaderboard report
Traffic Prediction BJTaxi ST-SSL MAPE (%) @ out 15.19 #1 of 5 Archive leaderboard report
Traffic Prediction NYCBike1 ST-SSL MAE @ in 4.94 #1 of 4 Archive leaderboard report
Traffic Prediction NYCBike1 ST-SSL MAE @ out 5.26 #1 of 4 Archive leaderboard report
Traffic Prediction NYCBike1 ST-SSL MAPE (%) @ in 23.69 #1 of 4 Archive leaderboard report
Traffic Prediction NYCBike1 ST-SSL MAPE (%) @ out 24.6 #1 of 4 Archive leaderboard report
Traffic Prediction NYCBike2 ST-SSL MAE @ in 5.04 #1 of 4 Archive leaderboard report
Traffic Prediction NYCBike2 ST-SSL MAE @ out 4.71 #1 of 4 Archive leaderboard report
Traffic Prediction NYCBike2 ST-SSL MAPE (%) @ in 22.54 #1 of 4 Archive leaderboard report
Traffic Prediction NYCBike2 ST-SSL MAPE (%) @ out 21.17 #1 of 4 Archive leaderboard report
Traffic Prediction NYCTaxi ST-SSL MAE @ in 11.99 #1 of 5 Archive leaderboard report
Traffic Prediction NYCTaxi ST-SSL MAE @ out 9.78 #1 of 5 Archive leaderboard report
Traffic Prediction NYCTaxi ST-SSL MAPE (%) @ in 16.38 #1 of 5 Archive leaderboard report
Traffic Prediction NYCTaxi ST-SSL MAPE (%) @ out 16.86 #1 of 5 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

fail

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