{"url":"/dataset/largest","name":"LargeST","full_name":"LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting","description_markdown":"In this work, we propose LargeST as a new benchmark dataset (see Figure 1), with the goal of facilitating the development of accurate and efficient methods in the context of large-scale traffic forecasting. The distinguishing characteristic of LargeST lies not only in its extensive graph size, encompassing a total of 8,600 sensors in California, but also in its substantial temporal coverage and rich node information – each sensor contains 5 years of data and comprehensive metadata. \r\n\r\nLargeST comprises four sub-datasets, each characterized by a different number of sensors. The biggest one is California (CA), including a total number of 8,600 sensors. We also construct three subsets of CA by selecting three representative areas within CA and forming the sub-datasets of Greater Los Angeles (GLA), Greater Bay Area (GBA), and San Diego (SD).","description_withheld":null,"homepage":"https://www.kaggle.com/datasets/liuxu77/largest","introduced_date":"2023-06-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/largest-a-benchmark-dataset-for-large-scale-1","title":"LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting","first_author":"Xu Liu","url":null},"license":{"name":"CC BY-NC 4.0 International License","url":"https://creativecommons.org/licenses/by-nc/4.0"},"modalities":[{"name":"Time series","url":"/datasets/modality/time-series"}],"tasks":[{"name":"Traffic Prediction","url":"/task/traffic-prediction","datasets_with_task":"/datasets/task/traffic-prediction"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["LargeST"],"data_loaders":[],"num_papers_in_archive":25,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/traffic-prediction-on-largest","task":"Traffic Prediction","dataset_variant":"LargeST","rows":6,"metrics":["SD MAE","GBA MAE","GLA MAE","CA MAE"],"first_row_in_archive_order":{"model":"PatchSTG","paper":"/paper/efficient-large-scale-traffic-forecasting","metrics":{"CA MAE":"17.35","GBA MAE":"19.50","GLA MAE":"18.96","SD MAE":"16.90"},"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"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/efficient-large-scale-traffic-forecasting","title":"Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspective","date":"2024-12-13","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":3,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/random-projection-layers-for-multidimensional","title":"RPMixer: Shaking Up Time Series Forecasting with Random Projections for Large Spatial-Temporal Data","date":"2024-02-16","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/when-spatio-temporal-meet-wavelets","title":"When Spatio-Temporal Meet Wavelets: Disentangled Traffic Forecasting via Efficient Spectral Graph Attention Networks","date":"2023-07-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/spatial-temporal-graph-ode-networks-for","title":"Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting","date":"2021-06-24","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/190600121","title":"Graph WaveNet for Deep Spatial-Temporal Graph Modeling","date":"2019-05-31","rows_on_this_dataset":1,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":5,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":16,"samples_ran":8,"samples_unverified":8,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}