Papers › Graph WaveNet for Deep Spatial-Temporal Graph Modeling

Graph WaveNet for Deep Spatial-Temporal Graph Modeling

31 May 2019arXiv:1906.00121archive 2025-07-28

Zonghan Wu, Shirui Pan, Guodong Long, Jing Jiang, Chengqi Zhang

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.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

No sample from the archive's official repository (nnzhan/Graph-WaveNet) is linked to this paper; the 7 samples below come from 3 community repositories. Syntology harvested code from nnzhan/Graph-WaveNet for another paper.

nnzhan/Graph-WaveNet: Syntology's graph links these samples to Enhancing Sustainable Urban Mobility Prediction with Telecom Data: A Spatio-Temporal... (arXiv:2405.17507; that paper's own run record: 8 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method.

Syntology 7 code samples harvested from 3 repositories linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 7 samples from 3 repositories, 5 ran (2 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

nnzhan/Graph-WaveNet officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Enhancing Sustainable Urban Mobility Prediction with Telecom Data: A Spatio-Temporal... (arXiv:2405.17507; that paper's own run record: 8 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
E666GT/TrafficPredictionNN mentioned on GitHubpytorchMITSyntology: not harvested report
JiahuiSun/Exp-Graph-WaveNet mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
LucaHermes/lightweight-motion-forecasting mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to WaveNet: A Generative Model for Raw Audio (arXiv:1609.03499; that paper's own run record: 65 ran (of which 23 constructed an object rather than computing a result; 52 with no instrument failure: 2 honoured, 1 violated, 49 with no contract checked; 13 where Syntology's instrument failed) · 38 unverified); nothing checks that they implement this paper's method. report
josegg05/eRGWnet mentioned on GitHubpytorchMITSyntology: not harvested report
razvanc92/enhancenet mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting (arXiv:1707.01926; that paper's own run record: 17 ran (of which 7 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 8 where Syntology's instrument failed) · 18 unverified); nothing checks that they implement this paper's method. report
simonvino/graphwavenet_brain_connectivity mentioned on GitHubpytorchMITSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
sshleifer/Graph-WaveNet mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
zachysun/taxi_traffic_benchmark mentioned on GitHubpytorchSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

7 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · violated contract
3ran · our draft was wrong
2unverified

Licence: 0 of the 7 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

JiahuiSun/Exp-Graph-WaveNet community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
seq_gen generate_training_data.py ran · our draft was wrong fingerprinted MIT (permissive) · 3028268c1774ed96 · report fixture: signature n_day:int/0/int, data_seq:ndarray/3/float, offset:int/0/int, n_frame:int/0/int, n_route:int/0/int, day_slot:int/0/int, C_0:int/0/int · returned ndarray · level recorded 2026-09-22
generate_graph_seq2seq_io_data in 10 papers generate_training_data.py unverified MIT (permissive) · fc148af599e95656 · report
simonvino/graphwavenet_brain_connectivity community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
generate_train_val_test generate_samples.py ran · our draft was wrong MIT (permissive) · c6093e02db929cdb · report fixture: signature input_dir:str/0/str, input_filename:str/0/str, output_dir:str/0/str, NSess:int/0/int, NSub:int/0/int, input_horizon:int/0/int, output_horizon:int/0/int, scaling:str/0/str, save_data:bool/0/bool, train_prop:float/0/float, test_prop:float/0/float, NROIs:int/0/int, perturbations:NoneType/0/? · returned tuple · level recorded 2026-09-22
generate_graph_seq2seq_io_data in 10 papers old_stuff/generate_training_data.py unverified MIT (permissive) · 1175f39f2d567546 · report
sshleifer/Graph-WaveNet community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
asym_adj in 9 papers util.py ran · violated contract MIT (permissive) · 901bedf723a6f00d · report fixture: signature adj:csr_matrix/2/float · returned matrix · level recorded 2026-09-22
calculate_normalized_laplacian in 11 papers util.py ran · our draft was wrong MIT (permissive) · e7b2e6a60daa42ca · report fixture: signature adj:csr_matrix/2/float · returned csr_matrix · level recorded 2026-09-22
sym_adj in 5 papers util.py ran · violated contract MIT (permissive) · 9a7928795f74526c · report fixture: signature adj:csr_matrix/2/float · returned matrix · level recorded 2026-09-22

Tasks

Graph Neural NetworkTemporal SequencesTraffic Prediction

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Traffic Prediction EXPY-TKY GWNet 1 step MAE 5.91 #4 of 8 Archive leaderboard report
Traffic Prediction EXPY-TKY GWNet 3 step MAE 6.59 #4 of 8 Archive leaderboard report
Traffic Prediction EXPY-TKY GWNet 6 step MAE 6.89 #4 of 8 Archive leaderboard report
Traffic Prediction LargeST GWNET CA MAE 21.72 #2 of 6 Archive leaderboard report
Traffic Prediction LargeST GWNET GBA MAE 20.91 #2 of 6 Archive leaderboard report
Traffic Prediction LargeST GWNET GLA MAE 21.20 #2 of 6 Archive leaderboard report
Traffic Prediction LargeST GWNET SD MAE 17.74 #2 of 6 Archive leaderboard report
Traffic Prediction METR-LA Graph WaveNet MAE @ 12 step 3.53 #17 of 20 Archive leaderboard report
Traffic Prediction METR-LA Graph WaveNet MAE @ 3 step 2.69 #17 of 20 Archive leaderboard report
Traffic Prediction NE-BJ Graph WaveNet 12 steps MAE 4.99 #5 of 6 Archive leaderboard report
Traffic Prediction PEMS-BAY Graph Wave-Net MAE @ 12 step 1.95 #13 of 16 Archive leaderboard report
Traffic Prediction PEMS-BAY Graph Wave-Net RMSE 4.52 #13 of 16 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

ConvolutionDilated Causal ConvolutionGraph Neural NetworkMixture of Logistic DistributionsWaveNet

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