{"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/modeling-tabular-data-using-conditional-gan","title":"Modeling Tabular data using Conditional GAN","arxiv_id":"1907.00503","date":"2019-07-01","proceeding":"NeurIPS 2019 12","authors":["Lei Xu","Maria Skoularidou","Alfredo Cuesta-Infante","Kalyan Veeramachaneni"],"abstract":"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.","url_abs":"https://arxiv.org/abs/1907.00503v2","url_pdf":"https://arxiv.org/pdf/1907.00503v2.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":"modeling-tabular-data-using-conditional-gan","repo_url":"https://github.com/DAI-Lab/CTGAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"modeling-tabular-data-using-conditional-gan","repo_url":"https://github.com/glederrey/datgan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"modeling-tabular-data-using-conditional-gan","repo_url":"https://github.com/juliecious/ctgan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"modeling-tabular-data-using-conditional-gan","repo_url":"https://github.com/oregonpillow/ctgan-server-cli","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"modeling-tabular-data-using-conditional-gan","repo_url":"https://github.com/saha0073/GAN-VAE-to-generate-Synthetic-Tabular-Data","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"modeling-tabular-data-using-conditional-gan","repo_url":"https://github.com/sdv-dev/CTGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"modeling-tabular-data-using-conditional-gan","repo_url":"https://github.com/Diyago/GAN-for-tabular-data","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"modeling-tabular-data-using-conditional-gan","repo_url":"https://github.com/lvyufeng/CTGAN-MindSpore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"modeling-tabular-data-using-conditional-gan","repo_url":"https://github.com/ydataai/ydata-synthetic/tree/dev/src/ydata_synthetic/synthesizers/regular/ctgan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"tabular-data-generation","task_name":"Tabular Data Generation"}],"methods":[],"datasets_introduced":[{"slug":"sdgym","name":"SDGym","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/tabular-data-generation-on-adult-census","task":"Tabular Data Generation","dataset":"Adult Census Income","model":"TVAE","rank_in_archive_order":4,"of":6,"metrics":{"DT Accuracy":"82.8","LR Accuracy":"80.53","Parameters(M)":"0.053","RF Accuracy":"83.48"},"uses_additional_data":false},{"leaderboard":"/sota/tabular-data-generation-on-adult-census","task":"Tabular Data Generation","dataset":"Adult Census Income","model":"CTGAN","rank_in_archive_order":5,"of":6,"metrics":{"DT Accuracy":"81.32","LR Accuracy":"83.2","Parameters(M)":"0.302","RF Accuracy":"83.53"},"uses_additional_data":false},{"leaderboard":"/sota/tabular-data-generation-on-adult-census","task":"Tabular Data Generation","dataset":"Adult Census Income","model":"CopulaGAN","rank_in_archive_order":6,"of":6,"metrics":{"DT Accuracy":"76.29","LR Accuracy":"80.61","Parameters(M)":"0.300","RF Accuracy":"80.46"},"uses_additional_data":false},{"leaderboard":"/sota/tabular-data-generation-on-california-housing","task":"Tabular Data Generation","dataset":"California Housing Prices","model":"TVAE","rank_in_archive_order":1,"of":6,"metrics":{"DT Mean Squared Error":"0.45","LR Mean Squared Error":"0.65","Parameters(M)":"0.045","RF Mean Squared Error":"0.35"},"uses_additional_data":false},{"leaderboard":"/sota/tabular-data-generation-on-california-housing","task":"Tabular Data Generation","dataset":"California Housing Prices","model":"CTGAN","rank_in_archive_order":2,"of":6,"metrics":{"DT Mean Squared Error":"0.82","LR Mean Squared Error":"0.61","Parameters(M)":"0.197","RF Mean Squared Error":"0.62"},"uses_additional_data":false},{"leaderboard":"/sota/tabular-data-generation-on-california-housing","task":"Tabular Data Generation","dataset":"California Housing Prices","model":"CopulaGAN","rank_in_archive_order":3,"of":6,"metrics":{"DT Mean Squared Error":"1.19","LR Mean Squared Error":"0.98","Parameters(M)":"0.201","RF Mean Squared Error":"0.99"},"uses_additional_data":false},{"leaderboard":"/sota/tabular-data-generation-on-diabetes","task":"Tabular Data Generation","dataset":"Diabetes","model":"TVAE","rank_in_archive_order":4,"of":6,"metrics":{"DT Accuracy":"0.5330","LR Accuracy":"0.5634","Parameters(M)":"0.359","RF Accuracy":"0.5517"},"uses_additional_data":false},{"leaderboard":"/sota/tabular-data-generation-on-diabetes","task":"Tabular Data Generation","dataset":"Diabetes","model":"CTGAN","rank_in_archive_order":5,"of":6,"metrics":{"DT Accuracy":"0.4973","LR Accuracy":"0.5093","Parameters(M)":"9.6","RF Accuracy":"0.5223"},"uses_additional_data":false},{"leaderboard":"/sota/tabular-data-generation-on-diabetes","task":"Tabular Data Generation","dataset":"Diabetes","model":"CopulaGAN","rank_in_archive_order":6,"of":6,"metrics":{"DT Accuracy":"0.385","LR Accuracy":"0.4027","Parameters(M)":"9.4","RF Accuracy":"0.3759"},"uses_additional_data":false},{"leaderboard":"/sota/tabular-data-generation-on-heloc","task":"Tabular Data Generation","dataset":"HELOC","model":"TVAE","rank_in_archive_order":3,"of":6,"metrics":{"DT Accuracy":"76.39","LR Accuracy":"71.04","Parameters(M)":"62","RF Accuracy":"77.24"},"uses_additional_data":false},{"leaderboard":"/sota/tabular-data-generation-on-heloc","task":"Tabular Data Generation","dataset":"HELOC","model":"CTGAN","rank_in_archive_order":5,"of":6,"metrics":{"DT Accuracy":"61.34","LR Accuracy":"57.72","Parameters(M)":"0.277","RF Accuracy":"62.35"},"uses_additional_data":false},{"leaderboard":"/sota/tabular-data-generation-on-heloc","task":"Tabular Data Generation","dataset":"HELOC","model":"CopulaGAN","rank_in_archive_order":6,"of":6,"metrics":{"DT Accuracy":"42.36","LR Accuracy":"42.03","Parameters(M)":"0.276","RF Accuracy":"42.35"},"uses_additional_data":false},{"leaderboard":"/sota/tabular-data-generation-on-sick","task":"Tabular Data Generation","dataset":"SICK","model":"TVAE","rank_in_archive_order":4,"of":6,"metrics":{"DT Accuracy":"95.39","LR Accuracy":"94.7","Parameters(M)":"0.046","RF Accuracy":"94.91"},"uses_additional_data":false},{"leaderboard":"/sota/tabular-data-generation-on-sick","task":"Tabular Data Generation","dataset":"SICK","model":"CopulaGAN","rank_in_archive_order":5,"of":6,"metrics":{"DT Accuracy":"93.77","LR Accuracy":"94.57","Parameters(M)":"0.226","RF Accuracy":"94.57"},"uses_additional_data":false},{"leaderboard":"/sota/tabular-data-generation-on-sick","task":"Tabular Data Generation","dataset":"SICK","model":"CTGAN","rank_in_archive_order":6,"of":6,"metrics":{"DT Accuracy":"92.05","LR Accuracy":"94.44","Parameters(M)":"0.222","RF Accuracy":"94.57"},"uses_additional_data":false},{"leaderboard":"/sota/tabular-data-generation-on-travel","task":"Tabular Data Generation","dataset":"Travel","model":"TVAE","rank_in_archive_order":3,"of":6,"metrics":{"DT Accuracy":"81.68","LR Accuracy":"79.58","Parameters(M)":"0.036","RF Accuracy":"81.68"},"uses_additional_data":false},{"leaderboard":"/sota/tabular-data-generation-on-travel","task":"Tabular Data Generation","dataset":"Travel","model":"CopulaGAN","rank_in_archive_order":5,"of":6,"metrics":{"DT Accuracy":"73.61","LR Accuracy":"73.3","Parameters(M)":"0.157","RF Accuracy":"73.3"},"uses_additional_data":false},{"leaderboard":"/sota/tabular-data-generation-on-travel","task":"Tabular Data Generation","dataset":"Travel","model":"CTGAN","rank_in_archive_order":6,"of":6,"metrics":{"DT Accuracy":"73.3","LR Accuracy":"73.3","Parameters(M)":"0.155","RF Accuracy":"71.41"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1907.00503","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.00503"}},"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/sdv-dev/CTGAN","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/oregonpillow/ctgan-server-cli","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/saha0073/GAN-VAE-to-generate-Synthetic-Tabular-Data","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/glederrey/datgan","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ydataai/ydata-synthetic/tree/dev/src/ydata_synthetic/synthesizers/regular/ctgan","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/juliecious/ctgan","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DAI-Lab/CTGAN","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Diyago/GAN-for-tabular-data","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lvyufeng/CTGAN-MindSpore","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"listed":{"samples":3,"ran":2,"repositories":2}},"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":"8c275cfb59a89271","entry":"read_csv","repo":"juliecious/ctgan","repo_kind":"listed","path":"ctgan/data.py","file_url":"https://github.com/juliecious/ctgan/blob/HEAD/ctgan/data.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8c275cfb59a89271"}},{"code_sha256_prefix":"6f6210a7fd883f29","entry":"read_tsv","repo":"juliecious/ctgan","repo_kind":"listed","path":"ctgan/data.py","file_url":"https://github.com/juliecious/ctgan/blob/HEAD/ctgan/data.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6f6210a7fd883f29"}},{"code_sha256_prefix":"a80d09bcb2ebc36f","entry":"grad_scale","repo":"lvyufeng/CTGAN-MindSpore","repo_kind":"listed","path":"ctgan/amp.py","file_url":"https://github.com/lvyufeng/CTGAN-MindSpore/blob/HEAD/ctgan/amp.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":"a80d09bcb2ebc36f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}