{"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/balanced-mixed-type-tabular-data-synthesis","title":"Balanced Mixed-Type Tabular Data Synthesis with Diffusion Models","arxiv_id":"2404.08254","date":"2024-04-12","proceeding":null,"authors":["Zeyu Yang","Han Yu","Peikun Guo","Khadija Zanna","Xiaoxue Yang","Akane Sano"],"abstract":"Diffusion models have emerged as a robust framework for various generative tasks, including tabular data synthesis. However, current tabular diffusion models tend to inherit bias in the training dataset and generate biased synthetic data, which may influence discriminatory actions. In this research, we introduce a novel tabular diffusion model that incorporates sensitive guidance to generate fair synthetic data with balanced joint distributions of the target label and sensitive attributes, such as sex and race. The empirical results demonstrate that our method effectively mitigates bias in training data while maintaining the quality of the generated samples. Furthermore, we provide evidence that our approach outperforms existing methods for synthesizing tabular data on fairness metrics such as demographic parity ratio and equalized odds ratio, achieving improvements of over $10\\%$. Our implementation is available at https://github.com/comp-well-org/fair-tab-diffusion.","url_abs":"https://arxiv.org/abs/2404.08254v2","url_pdf":"https://arxiv.org/pdf/2404.08254v2.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":"balanced-mixed-type-tabular-data-synthesis","repo_url":"https://github.com/comp-well-org/fair-tab-diffusion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"fairness","task_name":"Fairness"},{"task_slug":"tabular-data-generation","task_name":"Tabular Data Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.08254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.08254"}},"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/comp-well-org/fair-tab-diffusion","reach":{"status":"ok","spdx":"GPL-3.0"}}],"summary":{"ran":8},"by_repo_kind":{"official":{"samples":8,"ran":8,"repositories":1}},"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":8,"samples":[{"code_sha256_prefix":"ef25957cc0cb0f95","entry":"approx_standard_normal_cdf","repo":"comp-well-org/fair-tab-diffusion","repo_kind":"official","path":"src/diffusion/utils.py","file_url":"https://github.com/comp-well-org/fair-tab-diffusion/blob/HEAD/src/diffusion/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"ef25957cc0cb0f95"}},{"code_sha256_prefix":"f5ba27121316b7c0","entry":"betas_for_alpha_bar","repo":"comp-well-org/fair-tab-diffusion","repo_kind":"official","path":"src/diffusion/ddpm.py","file_url":"https://github.com/comp-well-org/fair-tab-diffusion/blob/HEAD/src/diffusion/ddpm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"f5ba27121316b7c0"}},{"code_sha256_prefix":"b5b9b4f74d476739","entry":"get_named_beta_schedule","repo":"comp-well-org/fair-tab-diffusion","repo_kind":"official","path":"src/diffusion/ddpm.py","file_url":"https://github.com/comp-well-org/fair-tab-diffusion/blob/HEAD/src/diffusion/ddpm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"b5b9b4f74d476739"}},{"code_sha256_prefix":"3aad45861278913d","entry":"group_norm","repo":"comp-well-org/fair-tab-diffusion","repo_kind":"official","path":"src/diffusion/unet.py","file_url":"https://github.com/comp-well-org/fair-tab-diffusion/blob/HEAD/src/diffusion/unet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"3aad45861278913d"}},{"code_sha256_prefix":"b5113db03e258353","entry":"normal_kl","repo":"comp-well-org/fair-tab-diffusion","repo_kind":"official","path":"src/diffusion/utils.py","file_url":"https://github.com/comp-well-org/fair-tab-diffusion/blob/HEAD/src/diffusion/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"b5113db03e258353"}},{"code_sha256_prefix":"4082fa134dd9d79d","entry":"sample","repo":"comp-well-org/fair-tab-diffusion","repo_kind":"official","path":"tabsyn/tabsyn/diffusion_utils.py","file_url":"https://github.com/comp-well-org/fair-tab-diffusion/blob/HEAD/tabsyn/tabsyn/diffusion_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"4082fa134dd9d79d"}},{"code_sha256_prefix":"076c864a096ef0c9","entry":"sample_step","repo":"comp-well-org/fair-tab-diffusion","repo_kind":"official","path":"tabsyn/tabsyn/diffusion_utils.py","file_url":"https://github.com/comp-well-org/fair-tab-diffusion/blob/HEAD/tabsyn/tabsyn/diffusion_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"076c864a096ef0c9"}},{"code_sha256_prefix":"dbedb10fdcc5bda0","entry":"timestep_embedding","repo":"comp-well-org/fair-tab-diffusion","repo_kind":"official","path":"src/diffusion/utils.py","file_url":"https://github.com/comp-well-org/fair-tab-diffusion/blob/HEAD/src/diffusion/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"dbedb10fdcc5bda0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}