{"url":"/task/traffic-prediction","name":"Traffic Prediction","slug":"traffic-prediction","description_markdown":"**Traffic Prediction** is a task that involves forecasting traffic conditions, such as the volume of vehicles and travel time, in a specific area or along a particular road. This task is important for optimizing transportation systems and reducing traffic congestion.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [BaiduTraffic](https://github.com/JingqingZ/BaiduTraffic) )</span>","categories":[{"name":"Time Series","url":"/area/time-series"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":375,"papers_with_code":164,"benchmarks":33,"benchmark_tables_in_archive":33,"benchmark_tables_shown":33,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":20,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/traffic-prediction-on-metr-la","slug":"traffic-prediction-on-metr-la","dataset":"METR-LA","dataset_url":"/dataset/metr-la","rows_in_archive":20,"metrics":["MAE @ 12 step","12 steps MAE","12 steps MAPE","12 steps RMSE","MAE @ 3 step"],"first_row_in_archive_order":{"model":"TITAN","paper_title":"A Time Series is Worth Five Experts: Heterogeneous Mixture of Experts for Traffic Flow Prediction","paper_url":"/paper/a-time-series-is-worth-five-experts-1","paper_date":"2024-09-26","arxiv_id":"2409.17440","code_links":[{"title":"sqlcow/TITAN","url":"https://github.com/sqlcow/TITAN"}],"syntology":null}},{"leaderboard":"/sota/traffic-prediction-on-pems07","slug":"traffic-prediction-on-pems07","dataset":"PeMS07","dataset_url":"/dataset/pems07","rows_in_archive":17,"metrics":["MAE@1h"],"first_row_in_archive_order":{"model":"STD-MAE","paper_title":"Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting","paper_url":"/paper/spatio-temporal-decoupled-masked-pre-training","paper_date":"2023-12-01","arxiv_id":"2312.00516","code_links":[{"title":"jimmy-7664/std-mae","url":"https://github.com/jimmy-7664/std-mae"}],"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}}},{"leaderboard":"/sota/traffic-prediction-on-pems-bay","slug":"traffic-prediction-on-pems-bay","dataset":"PEMS-BAY","dataset_url":"/dataset/pems-bay","rows_in_archive":16,"metrics":["MAE @ 12 step","RMSE ","RMSE"],"first_row_in_archive_order":{"model":"T-Graphormer","paper_title":"T-Graphormer: Using Transformers for Spatiotemporal Forecasting","paper_url":"/paper/t-graphormer-using-transformers-for","paper_date":"2025-01-22","arxiv_id":"2501.13274","code_links":[{"title":"rdh1115/T-Graphormer","url":"https://github.com/rdh1115/T-Graphormer"}],"syntology":null}},{"leaderboard":"/sota/traffic-prediction-on-pems08","slug":"traffic-prediction-on-pems08","dataset":"PeMS08","dataset_url":"/dataset/pems08","rows_in_archive":13,"metrics":["MAE@1h","FLOPs(M)","MAE","MAPE","Parameters(K)","RMSE"],"first_row_in_archive_order":{"model":"DTRformer","paper_title":"Dynamic Trend Fusion Module for Traffic Flow Prediction","paper_url":"/paper/dynamic-trend-fusion-module-for-traffic-flow","paper_date":"2025-01-18","arxiv_id":"2501.10796","code_links":[{"title":"hitplz/dstrformer","url":"https://github.com/hitplz/dstrformer"}],"syntology":null}},{"leaderboard":"/sota/traffic-prediction-on-pemsd4","slug":"traffic-prediction-on-pemsd4","dataset":"PeMSD4","dataset_url":"/dataset/pemsd4","rows_in_archive":13,"metrics":["12 steps MAE","12 steps MAPE","12 steps RMSE"],"first_row_in_archive_order":{"model":"Hierarchical-Attention-LSTM (HierAttnLSTM)","paper_title":"Network Level Spatial Temporal Traffic State Forecasting with Hierarchical Attention LSTM (HierAttnLSTM)","paper_url":"/paper/big-data-application-for-network-level-travel","paper_date":"2022-01-15","arxiv_id":"2201.05760","code_links":[{"title":"TeRyZh/Network-Level-Travel-Prediction-Hierarchical-Attention-LSTM","url":"https://github.com/TeRyZh/Network-Level-Travel-Prediction-Hierarchical-Attention-LSTM"}],"syntology":null}},{"leaderboard":"/sota/traffic-prediction-on-pemsd8","slug":"traffic-prediction-on-pemsd8","dataset":"PeMSD8","dataset_url":"/dataset/pemsd8","rows_in_archive":13,"metrics":["12 steps MAE","12 steps MAPE","12 steps RMSE","MAE@1h"],"first_row_in_archive_order":{"model":"Hierarchical-Attention-LSTM (HierAttnLSTM)","paper_title":"Network Level Spatial Temporal Traffic State Forecasting with Hierarchical Attention LSTM (HierAttnLSTM)","paper_url":"/paper/big-data-application-for-network-level-travel","paper_date":"2022-01-15","arxiv_id":"2201.05760","code_links":[{"title":"TeRyZh/Network-Level-Travel-Prediction-Hierarchical-Attention-LSTM","url":"https://github.com/TeRyZh/Network-Level-Travel-Prediction-Hierarchical-Attention-LSTM"}],"syntology":null}},{"leaderboard":"/sota/traffic-prediction-on-pems04","slug":"traffic-prediction-on-pems04","dataset":"PeMS04","dataset_url":"/dataset/pems04","rows_in_archive":12,"metrics":["12 Steps MAE","FLOPs(M)","MAE","MAPE","Parameters(K)","RMSE"],"first_row_in_archive_order":{"model":"STD-MAE","paper_title":"Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting","paper_url":"/paper/spatio-temporal-decoupled-masked-pre-training","paper_date":"2023-12-01","arxiv_id":"2312.00516","code_links":[{"title":"jimmy-7664/std-mae","url":"https://github.com/jimmy-7664/std-mae"}],"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}}},{"leaderboard":"/sota/traffic-prediction-on-expy-tky-1","slug":"traffic-prediction-on-expy-tky-1","dataset":"EXPY-TKY","dataset_url":"/dataset/expy-tky","rows_in_archive":8,"metrics":["1 step MAE","3 step MAE","6 step MAE"],"first_row_in_archive_order":{"model":"STD-MAE","paper_title":"Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting","paper_url":"/paper/spatio-temporal-decoupled-masked-pre-training","paper_date":"2023-12-01","arxiv_id":"2312.00516","code_links":[{"title":"jimmy-7664/std-mae","url":"https://github.com/jimmy-7664/std-mae"}],"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}}},{"leaderboard":"/sota/traffic-prediction-on-pemsd7","slug":"traffic-prediction-on-pemsd7","dataset":"PeMSD7","dataset_url":"/dataset/pemsd7","rows_in_archive":8,"metrics":["12 steps MAE","12 steps MAPE","12 steps RMSE"],"first_row_in_archive_order":{"model":"STD-MAE","paper_title":"Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting","paper_url":"/paper/spatio-temporal-decoupled-masked-pre-training","paper_date":"2023-12-01","arxiv_id":"2312.00516","code_links":[{"title":"jimmy-7664/std-mae","url":"https://github.com/jimmy-7664/std-mae"}],"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}}},{"leaderboard":"/sota/traffic-prediction-on-pemsd7-m","slug":"traffic-prediction-on-pemsd7-m","dataset":"PeMSD7(M)","dataset_url":null,"rows_in_archive":7,"metrics":["12 steps MAE","12 steps MAPE","12 steps RMSE"],"first_row_in_archive_order":{"model":"STD-MAE","paper_title":"Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting","paper_url":"/paper/spatio-temporal-decoupled-masked-pre-training","paper_date":"2023-12-01","arxiv_id":"2312.00516","code_links":[{"title":"jimmy-7664/std-mae","url":"https://github.com/jimmy-7664/std-mae"}],"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}}},{"leaderboard":"/sota/traffic-prediction-on-largest","slug":"traffic-prediction-on-largest","dataset":"LargeST","dataset_url":"/dataset/largest","rows_in_archive":6,"metrics":["SD MAE","GBA MAE","GLA MAE","CA MAE"],"first_row_in_archive_order":{"model":"PatchSTG","paper_title":"Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspective","paper_url":"/paper/efficient-large-scale-traffic-forecasting","paper_date":"2024-12-13","arxiv_id":"2412.09972","code_links":[{"title":"lmissher/stgnn","url":"https://github.com/lmissher/stgnn"},{"title":"lmissher/stwave","url":"https://github.com/lmissher/stwave"},{"title":"lmissher/patchstg","url":"https://github.com/lmissher/patchstg"}],"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":0}}},{"leaderboard":"/sota/traffic-prediction-on-ne-bj","slug":"traffic-prediction-on-ne-bj","dataset":"NE-BJ","dataset_url":null,"rows_in_archive":6,"metrics":["12 steps MAE"],"first_row_in_archive_order":{"model":"RGDAN","paper_title":"RGDAN: A random graph diffusion attention network for traffic prediction","paper_url":"/paper/rgdan-a-random-graph-diffusion-attention","paper_date":"2024-01-16","arxiv_id":null,"code_links":[{"title":"wengwenchao123/RGDAN","url":"https://github.com/wengwenchao123/RGDAN"}],"syntology":null}},{"leaderboard":"/sota/traffic-prediction-on-pemsd3","slug":"traffic-prediction-on-pemsd3","dataset":"PeMSD3","dataset_url":null,"rows_in_archive":6,"metrics":["12 steps MAE","12 steps MAPE","12 steps RMSE"],"first_row_in_archive_order":{"model":"STD-MAE","paper_title":"Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting","paper_url":"/paper/spatio-temporal-decoupled-masked-pre-training","paper_date":"2023-12-01","arxiv_id":"2312.00516","code_links":[{"title":"jimmy-7664/std-mae","url":"https://github.com/jimmy-7664/std-mae"}],"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}}},{"leaderboard":"/sota/traffic-prediction-on-pemsd7-l","slug":"traffic-prediction-on-pemsd7-l","dataset":"PeMSD7(L)","dataset_url":null,"rows_in_archive":6,"metrics":["12 steps MAE","12 steps MAPE","12 steps RMSE"],"first_row_in_archive_order":{"model":"STD-MAE","paper_title":"Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting","paper_url":"/paper/spatio-temporal-decoupled-masked-pre-training","paper_date":"2023-12-01","arxiv_id":"2312.00516","code_links":[{"title":"jimmy-7664/std-mae","url":"https://github.com/jimmy-7664/std-mae"}],"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}}},{"leaderboard":"/sota/traffic-prediction-on-bjtaxi","slug":"traffic-prediction-on-bjtaxi","dataset":"BJTaxi","dataset_url":null,"rows_in_archive":5,"metrics":["MAE @ in","MAE @ out","MAPE (%) @ in","MAPE (%) @ out"],"first_row_in_archive_order":{"model":"ST-SSL","paper_title":"Spatio-Temporal Self-Supervised Learning for Traffic Flow Prediction","paper_url":"/paper/spatio-temporal-self-supervised-learning-for","paper_date":"2022-12-07","arxiv_id":"2212.04475","code_links":[{"title":"echo-ji/st-ssl","url":"https://github.com/echo-ji/st-ssl"}],"syntology":null}},{"leaderboard":"/sota/traffic-prediction-on-nyctaxi","slug":"traffic-prediction-on-nyctaxi","dataset":"NYCTaxi","dataset_url":"/dataset/nyctaxi","rows_in_archive":5,"metrics":["MAE @ in","MAE @ out","MAPE (%) @ in","MAPE (%) @ out"],"first_row_in_archive_order":{"model":"ST-SSL","paper_title":"Spatio-Temporal Self-Supervised Learning for Traffic Flow Prediction","paper_url":"/paper/spatio-temporal-self-supervised-learning-for","paper_date":"2022-12-07","arxiv_id":"2212.04475","code_links":[{"title":"echo-ji/st-ssl","url":"https://github.com/echo-ji/st-ssl"}],"syntology":null}},{"leaderboard":"/sota/traffic-prediction-on-pems-m","slug":"traffic-prediction-on-pems-m","dataset":"PeMS-M","dataset_url":null,"rows_in_archive":5,"metrics":["MAE (60 min)"],"first_row_in_archive_order":{"model":"ST-UNet","paper_title":"ST-UNet: A Spatio-Temporal U-Network for Graph-structured Time Series Modeling","paper_url":"/paper/st-unet-a-spatio-temporal-u-network-for-graph","paper_date":"2019-03-13","arxiv_id":"1903.05631","code_links":[],"syntology":null}},{"leaderboard":"/sota/traffic-prediction-on-sz-taxi","slug":"traffic-prediction-on-sz-taxi","dataset":"SZ-Taxi","dataset_url":"/dataset/sz-taxi","rows_in_archive":5,"metrics":["MAE @ 15min","MAE @ 30min","MAE @ 45min","MAE @ 60min"],"first_row_in_archive_order":{"model":"factorized ST-TGCN","paper_title":"Spatial-Temporal Tensor Graph Convolutional Network for Traffic Prediction","paper_url":"/paper/spatial-temporal-tensor-graph-convolutional","paper_date":"2021-03-10","arxiv_id":"2103.06126","code_links":[],"syntology":null}},{"leaderboard":"/sota/traffic-prediction-on-nycbike1","slug":"traffic-prediction-on-nycbike1","dataset":"NYCBike1","dataset_url":"/dataset/nycbike1","rows_in_archive":4,"metrics":["MAE @ in","MAE @ out","MAPE (%) @ in","MAPE (%) @ out"],"first_row_in_archive_order":{"model":"ST-SSL","paper_title":"Spatio-Temporal Self-Supervised Learning for Traffic Flow Prediction","paper_url":"/paper/spatio-temporal-self-supervised-learning-for","paper_date":"2022-12-07","arxiv_id":"2212.04475","code_links":[{"title":"echo-ji/st-ssl","url":"https://github.com/echo-ji/st-ssl"}],"syntology":null}},{"leaderboard":"/sota/traffic-prediction-on-nycbike2","slug":"traffic-prediction-on-nycbike2","dataset":"NYCBike2","dataset_url":"/dataset/nycbike2","rows_in_archive":4,"metrics":["MAE @ in","MAE @ out","MAPE (%) @ in","MAPE (%) @ out"],"first_row_in_archive_order":{"model":"ST-SSL","paper_title":"Spatio-Temporal Self-Supervised Learning for Traffic Flow Prediction","paper_url":"/paper/spatio-temporal-self-supervised-learning-for","paper_date":"2022-12-07","arxiv_id":"2212.04475","code_links":[{"title":"echo-ji/st-ssl","url":"https://github.com/echo-ji/st-ssl"}],"syntology":null}},{"leaderboard":"/sota/traffic-prediction-on-beijing","slug":"traffic-prediction-on-beijing","dataset":"Beijing Traffic","dataset_url":"/dataset/beijing","rows_in_archive":1,"metrics":["MAE"],"first_row_in_archive_order":{"model":"MemDA","paper_title":"MemDA: Forecasting Urban Time Series with Memory-based Drift Adaptation","paper_url":"/paper/memda-forecasting-urban-time-series-with","paper_date":"2023-09-25","arxiv_id":"2309.14216","code_links":[{"title":"zekun-cai/koodos","url":"https://github.com/zekun-cai/koodos"},{"title":"deepkashiwa20/Urban_Concept_Drift","url":"https://github.com/deepkashiwa20/Urban_Concept_Drift"}],"syntology":null}},{"leaderboard":"/sota/traffic-prediction-on-hzme-inflow","slug":"traffic-prediction-on-hzme-inflow","dataset":"HZME(inflow)","dataset_url":null,"rows_in_archive":1,"metrics":["MAE@1h"],"first_row_in_archive_order":{"model":"CorrSTN","paper_title":"A Correlation Information-based Spatiotemporal Network for Traffic Flow Forecasting","paper_url":"/paper/a-correlation-information-based","paper_date":"2022-05-20","arxiv_id":"2205.10365","code_links":[{"title":"drownfish19/corrstn","url":"https://github.com/drownfish19/corrstn"},{"title":"bjtu-ccd-lab/corrstn","url":"https://github.com/bjtu-ccd-lab/corrstn"}],"syntology":null}},{"leaderboard":"/sota/traffic-prediction-on-hzme-outflow","slug":"traffic-prediction-on-hzme-outflow","dataset":"HZME(outflow)","dataset_url":null,"rows_in_archive":1,"metrics":["MAE@1h"],"first_row_in_archive_order":{"model":"CorrSTN","paper_title":"A Correlation Information-based Spatiotemporal Network for Traffic Flow Forecasting","paper_url":"/paper/a-correlation-information-based","paper_date":"2022-05-20","arxiv_id":"2205.10365","code_links":[{"title":"drownfish19/corrstn","url":"https://github.com/drownfish19/corrstn"},{"title":"bjtu-ccd-lab/corrstn","url":"https://github.com/bjtu-ccd-lab/corrstn"}],"syntology":null}},{"leaderboard":"/sota/traffic-prediction-on-pemsd4-10-days-training","slug":"traffic-prediction-on-pemsd4-10-days-training","dataset":"PeMSD4 (10 days' training data, 15min)","dataset_url":null,"rows_in_archive":1,"metrics":["MAE","MAPE","RMSE"],"first_row_in_archive_order":{"model":"DASTNet","paper_title":"Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities","paper_url":"/paper/domain-adversarial-spatial-temporal-network-a","paper_date":"2022-02-08","arxiv_id":"2202.03630","code_links":[{"title":"yihongt/dastnet","url":"https://github.com/yihongt/dastnet"}],"syntology":null}},{"leaderboard":"/sota/traffic-prediction-on-pemsd4-10-days-training-1","slug":"traffic-prediction-on-pemsd4-10-days-training-1","dataset":"PeMSD4 (10 days' training data, 30min)","dataset_url":null,"rows_in_archive":1,"metrics":["MAE","MAPE","RMSE"],"first_row_in_archive_order":{"model":"DASTNet","paper_title":"Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities","paper_url":"/paper/domain-adversarial-spatial-temporal-network-a","paper_date":"2022-02-08","arxiv_id":"2202.03630","code_links":[{"title":"yihongt/dastnet","url":"https://github.com/yihongt/dastnet"}],"syntology":null}},{"leaderboard":"/sota/traffic-prediction-on-pemsd4-10-days-training-2","slug":"traffic-prediction-on-pemsd4-10-days-training-2","dataset":"PeMSD4 (10 days' training data, 60min)","dataset_url":null,"rows_in_archive":1,"metrics":["MAE","MAPE","RMSE"],"first_row_in_archive_order":{"model":"DASTNet","paper_title":"Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities","paper_url":"/paper/domain-adversarial-spatial-temporal-network-a","paper_date":"2022-02-08","arxiv_id":"2202.03630","code_links":[{"title":"yihongt/dastnet","url":"https://github.com/yihongt/dastnet"}],"syntology":null}},{"leaderboard":"/sota/traffic-prediction-on-pemsd7-10-days-training","slug":"traffic-prediction-on-pemsd7-10-days-training","dataset":"PeMSD7 (10 days' training data, 15min)","dataset_url":null,"rows_in_archive":1,"metrics":["MAE","MAPE","RMSE"],"first_row_in_archive_order":{"model":"DASTNet","paper_title":"Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities","paper_url":"/paper/domain-adversarial-spatial-temporal-network-a","paper_date":"2022-02-08","arxiv_id":"2202.03630","code_links":[{"title":"yihongt/dastnet","url":"https://github.com/yihongt/dastnet"}],"syntology":null}},{"leaderboard":"/sota/traffic-prediction-on-pemsd7-10-days-training-1","slug":"traffic-prediction-on-pemsd7-10-days-training-1","dataset":"PeMSD7 (10 days' training data, 30min)","dataset_url":null,"rows_in_archive":1,"metrics":["MAE","MAPE","RMSE"],"first_row_in_archive_order":{"model":"DASTNet","paper_title":"Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities","paper_url":"/paper/domain-adversarial-spatial-temporal-network-a","paper_date":"2022-02-08","arxiv_id":"2202.03630","code_links":[{"title":"yihongt/dastnet","url":"https://github.com/yihongt/dastnet"}],"syntology":null}},{"leaderboard":"/sota/traffic-prediction-on-pemsd7-10-days-training-2","slug":"traffic-prediction-on-pemsd7-10-days-training-2","dataset":"PeMSD7 (10 days' training data, 60min)","dataset_url":null,"rows_in_archive":1,"metrics":["MAE","MAPE","RMSE"],"first_row_in_archive_order":{"model":"DASTNet","paper_title":"Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities","paper_url":"/paper/domain-adversarial-spatial-temporal-network-a","paper_date":"2022-02-08","arxiv_id":"2202.03630","code_links":[{"title":"yihongt/dastnet","url":"https://github.com/yihongt/dastnet"}],"syntology":null}},{"leaderboard":"/sota/traffic-prediction-on-pemsd8-10-days-training","slug":"traffic-prediction-on-pemsd8-10-days-training","dataset":"PeMSD8 (10 days' training data, 15min)","dataset_url":null,"rows_in_archive":1,"metrics":["MAE","MAPE","RMSE"],"first_row_in_archive_order":{"model":"DASTNet","paper_title":"Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities","paper_url":"/paper/domain-adversarial-spatial-temporal-network-a","paper_date":"2022-02-08","arxiv_id":"2202.03630","code_links":[{"title":"yihongt/dastnet","url":"https://github.com/yihongt/dastnet"}],"syntology":null}},{"leaderboard":"/sota/traffic-prediction-on-pemsd8-10-days-training-1","slug":"traffic-prediction-on-pemsd8-10-days-training-1","dataset":"PeMSD8 (10 days' training data, 30min)","dataset_url":null,"rows_in_archive":1,"metrics":["MAE","MAPE","RMSE"],"first_row_in_archive_order":{"model":"DASTNet","paper_title":"Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities","paper_url":"/paper/domain-adversarial-spatial-temporal-network-a","paper_date":"2022-02-08","arxiv_id":"2202.03630","code_links":[{"title":"yihongt/dastnet","url":"https://github.com/yihongt/dastnet"}],"syntology":null}},{"leaderboard":"/sota/traffic-prediction-on-pemsd8-10-days-training-2","slug":"traffic-prediction-on-pemsd8-10-days-training-2","dataset":"PeMSD8 (10 days' training data, 60min)","dataset_url":null,"rows_in_archive":1,"metrics":["MAE","MAPE","RMSE"],"first_row_in_archive_order":{"model":"DASTNet","paper_title":"Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities","paper_url":"/paper/domain-adversarial-spatial-temporal-network-a","paper_date":"2022-02-08","arxiv_id":"2202.03630","code_links":[{"title":"yihongt/dastnet","url":"https://github.com/yihongt/dastnet"}],"syntology":null}},{"leaderboard":"/sota/traffic-prediction-on-q-traffic","slug":"traffic-prediction-on-q-traffic","dataset":"Q-Traffic","dataset_url":"/dataset/q-traffic","rows_in_archive":1,"metrics":["MAPE"],"first_row_in_archive_order":{"model":"hybrid Seq2Seq","paper_title":"Deep Sequence Learning with Auxiliary Information for Traffic Prediction","paper_url":"/paper/deep-sequence-learning-with-auxiliary","paper_date":"2018-06-13","arxiv_id":"1806.07380","code_links":[{"title":"JingqingZ/BaiduTraffic","url":"https://github.com/JingqingZ/BaiduTraffic"}],"syntology":null}}],"datasets":[{"url":"/dataset/pemsd8","name":"PeMSD8","full_name":"","num_papers_in_archive":44},{"url":"/dataset/pems04","name":"PeMS04","full_name":"","num_papers_in_archive":37},{"url":"/dataset/metr-la","name":"METR-LA","full_name":"","num_papers_in_archive":36},{"url":"/dataset/pems-bay","name":"PEMS-BAY","full_name":"","num_papers_in_archive":34},{"url":"/dataset/pemsd7","name":"PeMSD7","full_name":"","num_papers_in_archive":26},{"url":"/dataset/largest","name":"LargeST","full_name":"LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting","num_papers_in_archive":25},{"url":"/dataset/pems07","name":"PeMS07","full_name":"","num_papers_in_archive":25},{"url":"/dataset/pemsd4","name":"PeMSD4","full_name":"","num_papers_in_archive":20},{"url":"/dataset/pems08","name":"PeMS08","full_name":"","num_papers_in_archive":17},{"url":"/dataset/nyctaxi","name":"NYCTaxi","full_name":"","num_papers_in_archive":12},{"url":"/dataset/expy-tky","name":"EXPY-TKY","full_name":"Expressway-Tokyo","num_papers_in_archive":9},{"url":"/dataset/q-traffic","name":"Q-Traffic","full_name":null,"num_papers_in_archive":6},{"url":"/dataset/nycbike1","name":"NYCBike1","full_name":"","num_papers_in_archive":4},{"url":"/dataset/nycbike2","name":"NYCBike2","full_name":"","num_papers_in_archive":4},{"url":"/dataset/sz-taxi","name":"SZ-Taxi","full_name":"Shenzhen Taxi Speed","num_papers_in_archive":4},{"url":"/dataset/beijing","name":"Beijing Traffic","full_name":"","num_papers_in_archive":1},{"url":"/dataset/equilibrium-traffic-networks","name":"Equilibrium-Traffic-Networks","full_name":"","num_papers_in_archive":1},{"url":"/dataset/grd-trt-buf-4i-technical-validation-data","name":"GRD-TRT-BUF-4I Technical Validation Data","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vluc","name":"VLUC","full_name":"Video-Like Urban Computing","num_papers_in_archive":1},{"url":"/dataset/ctv-dataset","name":"CTV-Dataset","full_name":"Cyclist Top-View Dataset","num_papers_in_archive":0}],"subtasks":[{"url":"/task/traffic-data-imputation","name":"Traffic Data Imputation"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":164,"tagged_in_all":375,"items":[{"url":"/paper/sequence-to-sequence-learning-with-neural","title":"Sequence to Sequence Learning with Neural Networks","date":"2014-09-10","arxiv_id":"1409.3215","repositories_listed":74,"syntology":{"n":25,"n_ran":11,"n_unverified":14,"n_pointer_only":9}},{"url":"/paper/diffusion-convolutional-recurrent-neural","title":"Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting","date":"2017-07-06","arxiv_id":"1707.01926","repositories_listed":19,"syntology":{"n":35,"n_ran":17,"n_unverified":18,"n_pointer_only":15}},{"url":"/paper/t-gcn-a-temporal-graph-convolutionalnetwork","title":"T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction","date":"2018-11-12","arxiv_id":"1811.05320","repositories_listed":10,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/190600121","title":"Graph WaveNet for Deep Spatial-Temporal Graph Modeling","date":"2019-05-31","arxiv_id":"1906.00121","repositories_listed":9,"syntology":{"n":7,"n_ran":5,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/spatio-temporal-graph-convolutional-networks","title":"Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting","date":"2017-09-14","arxiv_id":"1709.04875","repositories_listed":7,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/time-series-is-a-special-sequence-forecasting","title":"SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction","date":"2021-06-17","arxiv_id":"2106.09305","repositories_listed":6,"syntology":{"n":6,"n_ran":1,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/gman-a-graph-multi-attention-network-for","title":"GMAN: A Graph Multi-Attention Network for Traffic Prediction","date":"2019-11-11","arxiv_id":"1911.08415","repositories_listed":6,"syntology":{"n":10,"n_ran":0,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/revisiting-spatial-temporal-similarity-a-deep","title":"Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction","date":"2018-03-03","arxiv_id":"1803.01254","repositories_listed":5,"syntology":null},{"url":"/paper/incrementally-improving-graph-wavenet","title":"Incrementally Improving Graph WaveNet Performance on Traffic Prediction","date":"2019-12-11","arxiv_id":"1912.07390","repositories_listed":4,"syntology":null},{"url":"/paper/efficient-large-scale-traffic-forecasting","title":"Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspective","date":"2024-12-13","arxiv_id":"2412.09972","repositories_listed":3,"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/spatial-temporal-large-language-model-for","title":"Spatial-Temporal Large Language Model for Traffic Prediction","date":"2024-01-18","arxiv_id":"2401.10134","repositories_listed":3,"syntology":null},{"url":"/paper/dl-traff-survey-and-benchmark-of-deep","title":"DL-Traff: Survey and Benchmark of Deep Learning Models for Urban Traffic Prediction","date":"2021-08-20","arxiv_id":"2108.09091","repositories_listed":3,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/spectral-temporal-graph-neural-network-for-1","title":"Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting","date":"2021-03-13","arxiv_id":"2103.07719","repositories_listed":3,"syntology":{"n":13,"n_ran":2,"n_unverified":11,"n_pointer_only":2}},{"url":"/paper/adaptive-graph-convolutional-recurrent","title":"Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting","date":"2020-07-06","arxiv_id":"2007.02842","repositories_listed":3,"syntology":{"n":7,"n_ran":5,"n_unverified":2,"n_pointer_only":1}},{"url":"/paper/connecting-the-dots-multivariate-time-series","title":"Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks","date":"2020-05-24","arxiv_id":"2005.11650","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/bjtt-a-large-scale-multimodal-dataset-for","title":"BjTT: A Large-scale Multimodal Dataset for Traffic Prediction","date":"2024-03-08","arxiv_id":"2403.05029","repositories_listed":2,"syntology":null},{"url":"/paper/memda-forecasting-urban-time-series-with","title":"MemDA: Forecasting Urban Time Series with Memory-based Drift Adaptation","date":"2023-09-25","arxiv_id":"2309.14216","repositories_listed":2,"syntology":null},{"url":"/paper/stg4traffic-a-survey-and-benchmark-of-spatial","title":"STG4Traffic: A Survey and Benchmark of Spatial-Temporal Graph Neural Networks for Traffic Prediction","date":"2023-07-02","arxiv_id":"2307.00495","repositories_listed":2,"syntology":null},{"url":"/paper/traffnet-learning-causality-of-traffic","title":"TraffNet: Learning Causality of Traffic Generation for What-if Prediction","date":"2023-03-28","arxiv_id":"2303.15954","repositories_listed":2,"syntology":null},{"url":"/paper/graph-neural-rough-differential-equations-for","title":"Graph Neural Rough Differential Equations for Traffic Forecasting","date":"2023-03-20","arxiv_id":"2303.10909","repositories_listed":2,"syntology":{"n":17,"n_ran":6,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/multi-task-learning-for-sparse-traffic","title":"Multi-task Learning for Sparse Traffic Forecasting","date":"2022-11-18","arxiv_id":"2211.09984","repositories_listed":2,"syntology":null},{"url":"/paper/prompt-based-time-series-forecasting-a-new","title":"PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecasting","date":"2022-09-20","arxiv_id":"2210.08964","repositories_listed":2,"syntology":null},{"url":"/paper/spatial-temporal-identity-a-simple-yet","title":"Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting","date":"2022-08-10","arxiv_id":"2208.05233","repositories_listed":2,"syntology":null},{"url":"/paper/pre-training-enhanced-spatial-temporal-graph","title":"Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting","date":"2022-06-18","arxiv_id":"2206.09113","repositories_listed":2,"syntology":null},{"url":"/paper/a-correlation-information-based","title":"A Correlation Information-based Spatiotemporal Network for Traffic Flow Forecasting","date":"2022-05-20","arxiv_id":"2205.10365","repositories_listed":2,"syntology":null},{"url":"/paper/multivariate-time-series-forecasting-with-1","title":"Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs","date":"2022-02-17","arxiv_id":"2202.08408","repositories_listed":2,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/predicting-traffic-signals-on-transportation","title":"Traffic signal prediction on transportation networks using spatio-temporal correlations on graphs","date":"2021-04-27","arxiv_id":"2104.13414","repositories_listed":2,"syntology":null},{"url":"/paper/spatial-temporal-fusion-graph-neural-networks","title":"Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting","date":"2020-12-15","arxiv_id":"2012.09641","repositories_listed":2,"syntology":null},{"url":"/paper/spatial-temporal-synchronous-graph","title":"Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting","date":"2020-04-03","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/acfm-a-dynamic-spatial-temporal-network-for","title":"Dynamic Spatial-Temporal Representation Learning for Traffic Flow Prediction","date":"2019-09-02","arxiv_id":"1909.02902","repositories_listed":2,"syntology":null}],"syntology_records":14,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}