{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/190600121","title":"Graph WaveNet for Deep Spatial-Temporal Graph Modeling","arxiv_id":"1906.00121","date":"2019-05-31","proceeding":null,"authors":["Zonghan Wu","Shirui Pan","Guodong Long","Jing Jiang","Chengqi Zhang"],"abstract":"Spatial-temporal graph modeling is an important task to analyze the spatial relations and temporal trends of components in a system. Existing approaches mostly capture the spatial dependency on a fixed graph structure, assuming that the underlying relation between entities is pre-determined. However, the explicit graph structure (relation) does not necessarily reflect the true dependency and genuine relation may be missing due to the incomplete connections in the data. Furthermore, existing methods are ineffective to capture the temporal trends as the RNNs or CNNs employed in these methods cannot capture long-range temporal sequences. To overcome these limitations, we propose in this paper a novel graph neural network architecture, Graph WaveNet, for spatial-temporal graph modeling. By developing a novel adaptive dependency matrix and learn it through node embedding, our model can precisely capture the hidden spatial dependency in the data. With a stacked dilated 1D convolution component whose receptive field grows exponentially as the number of layers increases, Graph WaveNet is able to handle very long sequences. These two components are integrated seamlessly in a unified framework and the whole framework is learned in an end-to-end manner. Experimental results on two public traffic network datasets, METR-LA and PEMS-BAY, demonstrate the superior performance of our algorithm.","url_abs":"https://arxiv.org/abs/1906.00121v1","url_pdf":"https://arxiv.org/pdf/1906.00121v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"190600121","repo_url":"https://github.com/nnzhan/Graph-WaveNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"190600121","repo_url":"https://github.com/E666GT/TrafficPredictionNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"190600121","repo_url":"https://github.com/JiahuiSun/Exp-Graph-WaveNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"190600121","repo_url":"https://github.com/LucaHermes/lightweight-motion-forecasting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"190600121","repo_url":"https://github.com/josegg05/eRGWnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"190600121","repo_url":"https://github.com/razvanc92/enhancenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"190600121","repo_url":"https://github.com/simonvino/graphwavenet_brain_connectivity","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"190600121","repo_url":"https://github.com/sshleifer/Graph-WaveNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"190600121","repo_url":"https://github.com/zachysun/taxi_traffic_benchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"temporal-sequences","task_name":"Temporal Sequences"},{"task_slug":"traffic-prediction","task_name":"Traffic Prediction"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dilated-causal-convolution","method_name":"Dilated Causal Convolution"},{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"},{"method_slug":"mixture-of-logistic-distributions","method_name":"Mixture of Logistic Distributions"},{"method_slug":"wavenet","method_name":"WaveNet"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/traffic-prediction-on-expy-tky-1","task":"Traffic Prediction","dataset":"EXPY-TKY","model":"GWNet","rank_in_archive_order":4,"of":8,"metrics":{"1 step MAE":"5.91","3 step MAE":"6.59","6 step MAE":"6.89"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-prediction-on-largest","task":"Traffic Prediction","dataset":"LargeST","model":"GWNET","rank_in_archive_order":2,"of":6,"metrics":{"CA MAE":"21.72","GBA MAE":"20.91","GLA MAE":"21.20","SD MAE":"17.74"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-prediction-on-metr-la","task":"Traffic Prediction","dataset":"METR-LA","model":"Graph WaveNet","rank_in_archive_order":17,"of":20,"metrics":{"MAE @ 12 step":"3.53","MAE @ 3 step":"2.69"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-prediction-on-ne-bj","task":"Traffic Prediction","dataset":"NE-BJ","model":"Graph WaveNet","rank_in_archive_order":5,"of":6,"metrics":{"12 steps MAE":"4.99"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-prediction-on-pems-bay","task":"Traffic Prediction","dataset":"PEMS-BAY","model":"Graph Wave-Net","rank_in_archive_order":13,"of":16,"metrics":{"MAE @ 12 step":"1.95","RMSE":"4.52"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1906.00121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.00121"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nnzhan/Graph-WaveNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sshleifer/Graph-WaveNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/E666GT/TrafficPredictionNN","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JiahuiSun/Exp-Graph-WaveNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/simonvino/graphwavenet_brain_connectivity","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/josegg05/eRGWnet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zachysun/taxi_traffic_benchmark","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LucaHermes/lightweight-motion-forecasting","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/razvanc92/enhancenet","reach":null}],"summary":{"ran_violates":2,"ran_draft_wrong":3,"unverified":2},"by_repo_kind":{"listed":{"samples":7,"ran":5,"repositories":3}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"901bedf723a6f00d","entry":"asym_adj","repo":"sshleifer/Graph-WaveNet","repo_kind":"listed","path":"util.py","file_url":"https://github.com/sshleifer/Graph-WaveNet/blob/HEAD/util.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"901bedf723a6f00d"}},{"code_sha256_prefix":"e7b2e6a60daa42ca","entry":"calculate_normalized_laplacian","repo":"sshleifer/Graph-WaveNet","repo_kind":"listed","path":"util.py","file_url":"https://github.com/sshleifer/Graph-WaveNet/blob/HEAD/util.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e7b2e6a60daa42ca"}},{"code_sha256_prefix":"c6093e02db929cdb","entry":"generate_train_val_test","repo":"simonvino/graphwavenet_brain_connectivity","repo_kind":"listed","path":"generate_samples.py","file_url":"https://github.com/simonvino/graphwavenet_brain_connectivity/blob/HEAD/generate_samples.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c6093e02db929cdb"}},{"code_sha256_prefix":"3028268c1774ed96","entry":"seq_gen","repo":"JiahuiSun/Exp-Graph-WaveNet","repo_kind":"listed","path":"generate_training_data.py","file_url":"https://github.com/JiahuiSun/Exp-Graph-WaveNet/blob/HEAD/generate_training_data.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3028268c1774ed96"}},{"code_sha256_prefix":"9a7928795f74526c","entry":"sym_adj","repo":"sshleifer/Graph-WaveNet","repo_kind":"listed","path":"util.py","file_url":"https://github.com/sshleifer/Graph-WaveNet/blob/HEAD/util.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9a7928795f74526c"}},{"code_sha256_prefix":"fc148af599e95656","entry":"generate_graph_seq2seq_io_data","repo":"JiahuiSun/Exp-Graph-WaveNet","repo_kind":"listed","path":"generate_training_data.py","file_url":"https://github.com/JiahuiSun/Exp-Graph-WaveNet/blob/HEAD/generate_training_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fc148af599e95656"}},{"code_sha256_prefix":"1175f39f2d567546","entry":"generate_graph_seq2seq_io_data","repo":"simonvino/graphwavenet_brain_connectivity","repo_kind":"listed","path":"old_stuff/generate_training_data.py","file_url":"https://github.com/simonvino/graphwavenet_brain_connectivity/blob/HEAD/old_stuff/generate_training_data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1175f39f2d567546"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}