Papers › Graph Neural Rough Differential Equations for Traffic Forecasting

Graph Neural Rough Differential Equations for Traffic Forecasting

20 Mar 2023arXiv:2303.10909archive 2025-07-28

Jeongwhan Choi, Noseong Park

Traffic forecasting is one of the most popular spatio-temporal tasks in the field of machine learning. A prevalent approach in the field is to combine graph convolutional networks and recurrent neural networks for the spatio-temporal processing. There has been fierce competition and many novel methods have been proposed. In this paper, we present the method of spatio-temporal graph neural rough differential equation (STG-NRDE). Neural rough differential equations (NRDEs) are a breakthrough concept for processing time-series data. Their main concept is to use the log-signature transform to convert a time-series sample into a relatively shorter series of feature vectors. We extend the concept and design two NRDEs: one for the temporal processing and the other for the spatial processing. After that, we combine them into a single framework. We conduct experiments with 6 benchmark datasets and 27 baselines. STG-NRDE shows the best accuracy in all cases, outperforming all those 27 baselines by non-trivial margins.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2303.10909")

Code

Syntology Ran 6 of 17 code samples harvested from 1 repository linked to this paper; 11 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 5 ran with no contract checked.

By repository: official repository: 17 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

jeongwhanchoi/STG-NCDE officialmentioned in paperpytorchMIT report
jeongwhanchoi/stg-nrde 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

17 samples harvested; 6 ran; 0 honoured the contract we drafted; 11 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
5ran
11unverified

Licence: 0 of the 17 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 jeongwhanchoi/STG-NCDE. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

MSE_torch jeongwhanchoi/STG-NCDE/lib/metrics.py official repository ran fingerprinted MIT (permissive) · bb1134c39c66c490 · report
cdeint jeongwhanchoi/STG-NCDE/controldiffeq/cdeint_module.py official repository ran MIT (permissive) · a4dafc84cbeb2bb5 · report
get_logger jeongwhanchoi/STG-NCDE/lib/logger.py official repository ran MIT (permissive) · 996764623af1eab9 · report
init_lr_scheduler jeongwhanchoi/STG-NCDE/lib/TrainInits.py official repository ran MIT (permissive) · e246ed362e86604f · report
init_optim jeongwhanchoi/STG-NCDE/lib/TrainInits.py official repository ran MIT (permissive) · ffe6b5e6a255061f · report
split_data_by_ratio jeongwhanchoi/STG-NCDE/lib/dataloader.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · f06b9dde37d1edca · report
Add_Window_Horizon jeongwhanchoi/STG-NCDE/lib/add_window.py official repository unverified MIT (permissive) · be27678f7901f1dc · report
MAE_torch jeongwhanchoi/STG-NCDE/lib/metrics.py official repository unverified MIT (permissive) · 2d4043d05780769f · report
RMSE_torch jeongwhanchoi/STG-NCDE/lib/metrics.py official repository unverified MIT (permissive) · dadeb499af3778ba · report
cdeint_gde jeongwhanchoi/STG-NCDE/controldiffeq/cdeint_module.py official repository unverified MIT (permissive) · d11447048d8aee41 · report
cdeint_gde_dev jeongwhanchoi/STG-NCDE/controldiffeq/cdeint_module.py official repository unverified MIT (permissive) · f79327f4cedd197d · report
init_device jeongwhanchoi/STG-NCDE/lib/TrainInits.py official repository unverified MIT (permissive) · d7187fc207b2d503 · report
load_st_dataset jeongwhanchoi/STG-NCDE/lib/load_dataset.py official repository unverified MIT (permissive) · 691381e2874098e4 · report
make_model jeongwhanchoi/STG-NCDE/model/Make_model.py official repository unverified MIT (permissive) · 7747ed35840050f5 · report
minmax_by_column jeongwhanchoi/STG-NCDE/lib/normalization.py official repository unverified MIT (permissive) · 0ef827883d7bf3e6 · report
one_hot_by_column jeongwhanchoi/STG-NCDE/lib/normalization.py official repository unverified MIT (permissive) · 132385707ec527a2 · report
split_data_by_days jeongwhanchoi/STG-NCDE/lib/dataloader.py official repository unverified MIT (permissive) · 8266f31f7ee7c353 · report

Tasks

Time SeriesTraffic Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Traffic Prediction PeMSD3 STG-NRDE 12 steps MAE 15.50 #5 of 6 Archive leaderboard report
Traffic Prediction PeMSD3 STG-NRDE 12 steps MAPE 14.9 #5 of 6 Archive leaderboard report
Traffic Prediction PeMSD3 STG-NRDE 12 steps RMSE 27.06 #5 of 6 Archive leaderboard report
Traffic Prediction PeMSD4 STG-NRDE 12 steps MAE 19.13 #12 of 13 Archive leaderboard report
Traffic Prediction PeMSD4 STG-NRDE 12 steps MAPE 12.68 #12 of 13 Archive leaderboard report
Traffic Prediction PeMSD4 STG-NRDE 12 steps RMSE 30.94 #12 of 13 Archive leaderboard report
Traffic Prediction PeMSD7 STG-NRDE 12 steps MAE 20.45 #7 of 8 Archive leaderboard report
Traffic Prediction PeMSD7 STG-NRDE 12 steps MAPE 8.65 #7 of 8 Archive leaderboard report
Traffic Prediction PeMSD7 STG-NRDE 12 steps RMSE 33.73 #7 of 8 Archive leaderboard report
Traffic Prediction PeMSD7(L) STG-NRDE 12 steps MAE 2.85 #5 of 6 Archive leaderboard report
Traffic Prediction PeMSD7(L) STG-NRDE 12 steps MAPE 7.14 #5 of 6 Archive leaderboard report
Traffic Prediction PeMSD7(L) STG-NRDE 12 steps RMSE 5.76 #5 of 6 Archive leaderboard report
Traffic Prediction PeMSD7(M) STG-NRDE 12 steps MAE 2.66 #5 of 7 Archive leaderboard report
Traffic Prediction PeMSD7(M) STG-NRDE 12 steps MAPE 6.68 #5 of 7 Archive leaderboard report
Traffic Prediction PeMSD7(M) STG-NRDE 12 steps RMSE 5.31 #5 of 7 Archive leaderboard report
Traffic Prediction PeMSD8 STG-NRDE 12 steps MAE 15.32 #12 of 13 Archive leaderboard report
Traffic Prediction PeMSD8 STG-NRDE 12 steps MAPE 8.9 #12 of 13 Archive leaderboard report
Traffic Prediction PeMSD8 STG-NRDE 12 steps RMSE 24.72 #12 of 13 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

FIERCE

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