Papers › Modeling Tabular data using Conditional GAN

Modeling Tabular data using Conditional GAN

1 Jul 2019NeurIPS 2019 12arXiv:1907.00503archive 2025-07-28

Lei Xu, Maria Skoularidou, Alfredo Cuesta-Infante, Kalyan Veeramachaneni

Modeling the probability distribution of rows in tabular data and generating realistic synthetic data is a non-trivial task. Tabular data usually contains a mix of discrete and continuous columns. Continuous columns may have multiple modes whereas discrete columns are sometimes imbalanced making the modeling difficult. Existing statistical and deep neural network models fail to properly model this type of data. We design TGAN, which uses a conditional generative adversarial network to address these challenges. To aid in a fair and thorough comparison, we design a benchmark with 7 simulated and 8 real datasets and several Bayesian network baselines. TGAN outperforms Bayesian methods on most of the real datasets whereas other deep learning methods could not.

PaperPDFConference PDFCodeCode 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

The archive's official repository (DAI-Lab/CTGAN) was not harvested; the 3 samples below come from 2 community repositories.

Syntology 3 code samples harvested from 2 repositories linked to this paper: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 3 samples from 2 repositories, 2 ran (2 with no instrument failure; 0 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 2 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

DAI-Lab/CTGAN officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
glederrey/datgan mentioned on GitHubtfGPL-3.0Syntology: not harvested report
juliecious/ctgan mentioned on GitHubpytorchMITSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
oregonpillow/ctgan-server-cli mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
saha0073/GAN-VAE-to-generate-Synthetic-Tabular-Data mentioned on GitHubSyntology: not harvested report
sdv-dev/CTGAN mentioned on GitHubpytorchNOASSERTIONSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Continuous Diffusion for Mixed-Type Tabular Data (arXiv:2312.10431; that paper's own run record: 21 ran (of which 5 constructed an object rather than computing a result; 15 with no instrument failure: 4 honoured, 1 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
Diyago/GAN-for-tabular-data pytorchSyntology: not harvested report
lvyufeng/CTGAN-MindSpore mindsporeMITSyntology: 1 sample, 0 ran · 1 unverified report
ydataai/ydata-synthetic tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Improved Training of Wasserstein GANs (arXiv:1704.00028; that paper's own run record: 27 ran (of which 10 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 0 violated, 18 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified); nothing checks that they implement this paper's method. 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

3 samples harvested: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 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
1unverified

Licence: 2 of the 3 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

juliecious/ctgan community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
read_csv in 60 papers ctgan/data.py ran MIT (permissive) here; the stored copy is pointer only · 8c275cfb59a89271 · report fixture: signature csv_filename:str/0/str, meta_filename:str/0/str, header:bool/0/bool, discrete:NoneType/0/? · returned tuple · level recorded 2026-09-24
read_tsv in 13 papers ctgan/data.py ran MIT (permissive) here; the stored copy is pointer only · 6f6210a7fd883f29 · report fixture: signature data_filename:str/0/str, meta_filename:str/0/str · returned tuple · level recorded 2026-09-24
lvyufeng/CTGAN-MindSpore community (archive-listed) 1 sample, 0 ran · 1 unverified
grad_scale in 16 papers
census: 3 implementations from 8 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
ctgan/amp.py unverified MIT (permissive) · a80d09bcb2ebc36f · report

Tasks

Tabular Data Generation

1 archive task tag without a task page not shown.

Datasets

Introduced by this paper, per the archive.

SDGym

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Tabular Data Generation Adult Census Income TVAE DT Accuracy 82.8 #4 of 6 Archive leaderboard report
Tabular Data Generation Adult Census Income TVAE LR Accuracy 80.53 #4 of 6 Archive leaderboard report
Tabular Data Generation Adult Census Income TVAE Parameters(M) 0.053 #4 of 6 Archive leaderboard report
Tabular Data Generation Adult Census Income TVAE RF Accuracy 83.48 #4 of 6 Archive leaderboard report
Tabular Data Generation Adult Census Income CTGAN DT Accuracy 81.32 #5 of 6 Archive leaderboard report
Tabular Data Generation Adult Census Income CTGAN LR Accuracy 83.2 #5 of 6 Archive leaderboard report
Tabular Data Generation Adult Census Income CTGAN Parameters(M) 0.302 #5 of 6 Archive leaderboard report
Tabular Data Generation Adult Census Income CTGAN RF Accuracy 83.53 #5 of 6 Archive leaderboard report
Tabular Data Generation Adult Census Income CopulaGAN DT Accuracy 76.29 #6 of 6 Archive leaderboard report
Tabular Data Generation Adult Census Income CopulaGAN LR Accuracy 80.61 #6 of 6 Archive leaderboard report
Tabular Data Generation Adult Census Income CopulaGAN Parameters(M) 0.300 #6 of 6 Archive leaderboard report
Tabular Data Generation Adult Census Income CopulaGAN RF Accuracy 80.46 #6 of 6 Archive leaderboard report
Tabular Data Generation California Housing Prices TVAE DT Mean Squared Error 0.45 #1 of 6 Archive leaderboard report
Tabular Data Generation California Housing Prices TVAE LR Mean Squared Error 0.65 #1 of 6 Archive leaderboard report
Tabular Data Generation California Housing Prices TVAE Parameters(M) 0.045 #1 of 6 Archive leaderboard report
Tabular Data Generation California Housing Prices TVAE RF Mean Squared Error 0.35 #1 of 6 Archive leaderboard report
Tabular Data Generation California Housing Prices CTGAN DT Mean Squared Error 0.82 #2 of 6 Archive leaderboard report
Tabular Data Generation California Housing Prices CTGAN LR Mean Squared Error 0.61 #2 of 6 Archive leaderboard report
Tabular Data Generation California Housing Prices CTGAN Parameters(M) 0.197 #2 of 6 Archive leaderboard report
Tabular Data Generation California Housing Prices CTGAN RF Mean Squared Error 0.62 #2 of 6 Archive leaderboard report
Tabular Data Generation California Housing Prices CopulaGAN DT Mean Squared Error 1.19 #3 of 6 Archive leaderboard report
Tabular Data Generation California Housing Prices CopulaGAN LR Mean Squared Error 0.98 #3 of 6 Archive leaderboard report
Tabular Data Generation California Housing Prices CopulaGAN Parameters(M) 0.201 #3 of 6 Archive leaderboard report
Tabular Data Generation California Housing Prices CopulaGAN RF Mean Squared Error 0.99 #3 of 6 Archive leaderboard report
Tabular Data Generation Diabetes TVAE DT Accuracy 0.5330 #4 of 6 Archive leaderboard report
Tabular Data Generation Diabetes TVAE LR Accuracy 0.5634 #4 of 6 Archive leaderboard report
Tabular Data Generation Diabetes TVAE Parameters(M) 0.359 #4 of 6 Archive leaderboard report
Tabular Data Generation Diabetes TVAE RF Accuracy 0.5517 #4 of 6 Archive leaderboard report
Tabular Data Generation Diabetes CTGAN DT Accuracy 0.4973 #5 of 6 Archive leaderboard report
Tabular Data Generation Diabetes CTGAN LR Accuracy 0.5093 #5 of 6 Archive leaderboard report
Tabular Data Generation Diabetes CTGAN Parameters(M) 9.6 #5 of 6 Archive leaderboard report
Tabular Data Generation Diabetes CTGAN RF Accuracy 0.5223 #5 of 6 Archive leaderboard report
Tabular Data Generation Diabetes CopulaGAN DT Accuracy 0.385 #6 of 6 Archive leaderboard report
Tabular Data Generation Diabetes CopulaGAN LR Accuracy 0.4027 #6 of 6 Archive leaderboard report
Tabular Data Generation Diabetes CopulaGAN Parameters(M) 9.4 #6 of 6 Archive leaderboard report
Tabular Data Generation Diabetes CopulaGAN RF Accuracy 0.3759 #6 of 6 Archive leaderboard report
Tabular Data Generation HELOC TVAE DT Accuracy 76.39 #3 of 6 Archive leaderboard report
Tabular Data Generation HELOC TVAE LR Accuracy 71.04 #3 of 6 Archive leaderboard report
Tabular Data Generation HELOC TVAE Parameters(M) 62 #3 of 6 Archive leaderboard report
Tabular Data Generation HELOC TVAE RF Accuracy 77.24 #3 of 6 Archive leaderboard report
Tabular Data Generation HELOC CTGAN DT Accuracy 61.34 #5 of 6 Archive leaderboard report
Tabular Data Generation HELOC CTGAN LR Accuracy 57.72 #5 of 6 Archive leaderboard report
Tabular Data Generation HELOC CTGAN Parameters(M) 0.277 #5 of 6 Archive leaderboard report
Tabular Data Generation HELOC CTGAN RF Accuracy 62.35 #5 of 6 Archive leaderboard report
Tabular Data Generation HELOC CopulaGAN DT Accuracy 42.36 #6 of 6 Archive leaderboard report
Tabular Data Generation HELOC CopulaGAN LR Accuracy 42.03 #6 of 6 Archive leaderboard report
Tabular Data Generation HELOC CopulaGAN Parameters(M) 0.276 #6 of 6 Archive leaderboard report
Tabular Data Generation HELOC CopulaGAN RF Accuracy 42.35 #6 of 6 Archive leaderboard report
Tabular Data Generation SICK TVAE DT Accuracy 95.39 #4 of 6 Archive leaderboard report
Tabular Data Generation SICK TVAE LR Accuracy 94.7 #4 of 6 Archive leaderboard report
Tabular Data Generation SICK TVAE Parameters(M) 0.046 #4 of 6 Archive leaderboard report
Tabular Data Generation SICK TVAE RF Accuracy 94.91 #4 of 6 Archive leaderboard report
Tabular Data Generation SICK CopulaGAN DT Accuracy 93.77 #5 of 6 Archive leaderboard report
Tabular Data Generation SICK CopulaGAN LR Accuracy 94.57 #5 of 6 Archive leaderboard report
Tabular Data Generation SICK CopulaGAN Parameters(M) 0.226 #5 of 6 Archive leaderboard report
Tabular Data Generation SICK CopulaGAN RF Accuracy 94.57 #5 of 6 Archive leaderboard report
Tabular Data Generation SICK CTGAN DT Accuracy 92.05 #6 of 6 Archive leaderboard report
Tabular Data Generation SICK CTGAN LR Accuracy 94.44 #6 of 6 Archive leaderboard report
Tabular Data Generation SICK CTGAN Parameters(M) 0.222 #6 of 6 Archive leaderboard report
Tabular Data Generation SICK CTGAN RF Accuracy 94.57 #6 of 6 Archive leaderboard report
Tabular Data Generation Travel TVAE DT Accuracy 81.68 #3 of 6 Archive leaderboard report
Tabular Data Generation Travel TVAE LR Accuracy 79.58 #3 of 6 Archive leaderboard report
Tabular Data Generation Travel TVAE Parameters(M) 0.036 #3 of 6 Archive leaderboard report
Tabular Data Generation Travel TVAE RF Accuracy 81.68 #3 of 6 Archive leaderboard report
Tabular Data Generation Travel CopulaGAN DT Accuracy 73.61 #5 of 6 Archive leaderboard report
Tabular Data Generation Travel CopulaGAN LR Accuracy 73.3 #5 of 6 Archive leaderboard report
Tabular Data Generation Travel CopulaGAN Parameters(M) 0.157 #5 of 6 Archive leaderboard report
Tabular Data Generation Travel CopulaGAN RF Accuracy 73.3 #5 of 6 Archive leaderboard report
Tabular Data Generation Travel CTGAN DT Accuracy 73.3 #6 of 6 Archive leaderboard report
Tabular Data Generation Travel CTGAN LR Accuracy 73.3 #6 of 6 Archive leaderboard report
Tabular Data Generation Travel CTGAN Parameters(M) 0.155 #6 of 6 Archive leaderboard report
Tabular Data Generation Travel CTGAN RF Accuracy 71.41 #6 of 6 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.

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