{"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/mixed-type-tabular-data-synthesis-with-score","title":"Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space","arxiv_id":"2310.09656","date":"2023-10-14","proceeding":null,"authors":["Hengrui Zhang","Jiani Zhang","Balasubramaniam Srinivasan","Zhengyuan Shen","Xiao Qin","Christos Faloutsos","Huzefa Rangwala","George Karypis"],"abstract":"Recent advances in tabular data generation have greatly enhanced synthetic data quality. However, extending diffusion models to tabular data is challenging due to the intricately varied distributions and a blend of data types of tabular data. This paper introduces Tabsyn, a methodology that synthesizes tabular data by leveraging a diffusion model within a variational autoencoder (VAE) crafted latent space. The key advantages of the proposed Tabsyn include (1) Generality: the ability to handle a broad spectrum of data types by converting them into a single unified space and explicitly capture inter-column relations; (2) Quality: optimizing the distribution of latent embeddings to enhance the subsequent training of diffusion models, which helps generate high-quality synthetic data, (3) Speed: much fewer number of reverse steps and faster synthesis speed than existing diffusion-based methods. Extensive experiments on six datasets with five metrics demonstrate that Tabsyn outperforms existing methods. Specifically, it reduces the error rates by 86% and 67% for column-wise distribution and pair-wise column correlation estimations compared with the most competitive baselines.","url_abs":"https://arxiv.org/abs/2310.09656v3","url_pdf":"https://arxiv.org/pdf/2310.09656v3.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":"mixed-type-tabular-data-synthesis-with-score","repo_url":"https://github.com/amazon-science/tabsyn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"tabular-data-generation","task_name":"Tabular Data Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.09656","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.09656"}},"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":"deterministic:regex_extraction","url":"https://github.com/amazon-science/tabsyn","reach":null}],"summary":{"ran":3,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":0,"samples":[{"code_sha256_prefix":"46eef05b98790355","entry":"EDMLoss","repo":"amazon-science/tabsyn","repo_kind":"official","path":"tabsyn/model.py","file_url":"https://github.com/amazon-science/tabsyn/blob/HEAD/tabsyn/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"46eef05b98790355"}},{"code_sha256_prefix":"5608f882c4d890ea","entry":"Model","repo":"amazon-science/tabsyn","repo_kind":"official","path":"tabsyn/model.py","file_url":"https://github.com/amazon-science/tabsyn/blob/HEAD/tabsyn/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5608f882c4d890ea"}},{"code_sha256_prefix":"5f78805edc9c126e","entry":"Precond","repo":"amazon-science/tabsyn","repo_kind":"official","path":"tabsyn/model.py","file_url":"https://github.com/amazon-science/tabsyn/blob/HEAD/tabsyn/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5f78805edc9c126e"}},{"code_sha256_prefix":"1c17b2f36fed33d5","entry":"reorder","repo":"amazon-science/tabsyn","repo_kind":"official","path":"eval/eval_density.py","file_url":"https://github.com/amazon-science/tabsyn/blob/HEAD/eval/eval_density.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1c17b2f36fed33d5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}