{"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/tabrep-a-simple-and-effective-continuous","title":"TabRep: a Simple and Effective Continuous Representation for Training Tabular Diffusion Models","arxiv_id":"2504.04798","date":"2025-04-07","proceeding":null,"authors":["Jacob Si","Zijing Ou","Mike Qu","Zhengrui Xiang","Yingzhen Li"],"abstract":"Diffusion models have been the predominant generative model for tabular data generation. However, they face the conundrum of modeling under a separate versus a unified data representation. The former encounters the challenge of jointly modeling all multi-modal distributions of tabular data in one model. While the latter alleviates this by learning a single representation for all features, it currently leverages sparse suboptimal encoding heuristics and necessitates additional computation costs. In this work, we address the latter by presenting TabRep, a tabular diffusion architecture trained with a unified continuous representation. To motivate the design of our representation, we provide geometric insights into how the data manifold affects diffusion models. The key attributes of our representation are composed of its density, flexibility to provide ample separability for nominal features, and ability to preserve intrinsic relationships. Ultimately, TabRep provides a simple yet effective approach for training tabular diffusion models under a continuous data manifold. Our results showcase that TabRep achieves superior performance across a broad suite of evaluations. It is the first to synthesize tabular data that exceeds the downstream quality of the original datasets while preserving privacy and remaining computationally efficient.","url_abs":"https://arxiv.org/abs/2504.04798v2","url_pdf":"https://arxiv.org/pdf/2504.04798v2.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":"tabrep-a-simple-and-effective-continuous","repo_url":"https://github.com/jacobyhsi/TabRep","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"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=2504.04798","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.04798"}},"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/jacobyhsi/TabRep","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":2,"ran_draft_wrong":4,"ran_fixture":2,"ran":1,"unverified":10},"by_repo_kind":{"official":{"samples":19,"ran":9,"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":"9deab2a47adbf3b7","entry":"approx_standard_normal_cdf","repo":"jacobyhsi/TabRep","repo_kind":"official","path":"tabrep_ddpm/models/utils.py","file_url":"https://github.com/jacobyhsi/TabRep/blob/HEAD/tabrep_ddpm/models/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9deab2a47adbf3b7"}},{"code_sha256_prefix":"6cdc8772f5db6f48","entry":"betas_for_alpha_bar","repo":"jacobyhsi/TabRep","repo_kind":"official","path":"tabrep_ddpm/models/gaussian_multinomial_distribution.py","file_url":"https://github.com/jacobyhsi/TabRep/blob/HEAD/tabrep_ddpm/models/gaussian_multinomial_distribution.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6cdc8772f5db6f48"}},{"code_sha256_prefix":"6b6f39a3cb3edfa0","entry":"discretized_gaussian_log_likelihood","repo":"jacobyhsi/TabRep","repo_kind":"official","path":"tabrep_ddpm/models/utils.py","file_url":"https://github.com/jacobyhsi/TabRep/blob/HEAD/tabrep_ddpm/models/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6b6f39a3cb3edfa0"}},{"code_sha256_prefix":"49f8fe0655f00ee5","entry":"geglu","repo":"jacobyhsi/TabRep","repo_kind":"official","path":"tabrep_ddpm/models/modules.py","file_url":"https://github.com/jacobyhsi/TabRep/blob/HEAD/tabrep_ddpm/models/modules.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"49f8fe0655f00ee5"}},{"code_sha256_prefix":"141937afc98f8d1e","entry":"get_named_beta_schedule","repo":"jacobyhsi/TabRep","repo_kind":"official","path":"tabrep_ddpm/models/gaussian_multinomial_distribution.py","file_url":"https://github.com/jacobyhsi/TabRep/blob/HEAD/tabrep_ddpm/models/gaussian_multinomial_distribution.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"141937afc98f8d1e"}},{"code_sha256_prefix":"4707efa98ac6b989","entry":"normal_kl","repo":"jacobyhsi/TabRep","repo_kind":"official","path":"tabrep_ddpm/models/utils.py","file_url":"https://github.com/jacobyhsi/TabRep/blob/HEAD/tabrep_ddpm/models/utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4707efa98ac6b989"}},{"code_sha256_prefix":"eeb5b8effffc6cdd","entry":"pad_t_like_x","repo":"jacobyhsi/TabRep","repo_kind":"official","path":"tabrep_flow/models/flow_matching.py","file_url":"https://github.com/jacobyhsi/TabRep/blob/HEAD/tabrep_flow/models/flow_matching.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eeb5b8effffc6cdd"}},{"code_sha256_prefix":"58bd3831c7fb6729","entry":"reglu","repo":"jacobyhsi/TabRep","repo_kind":"official","path":"tabrep_ddpm/models/modules.py","file_url":"https://github.com/jacobyhsi/TabRep/blob/HEAD/tabrep_ddpm/models/modules.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"58bd3831c7fb6729"}},{"code_sha256_prefix":"6c617b25817f8107","entry":"timestep_embedding","repo":"jacobyhsi/TabRep","repo_kind":"official","path":"tabrep_flow/models/modules.py","file_url":"https://github.com/jacobyhsi/TabRep/blob/HEAD/tabrep_flow/models/modules.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6c617b25817f8107"}},{"code_sha256_prefix":"12ed451084a39969","entry":"bits_needed","repo":"jacobyhsi/TabRep","repo_kind":"official","path":"tabrep_ddpm/sample.py","file_url":"https://github.com/jacobyhsi/TabRep/blob/HEAD/tabrep_ddpm/sample.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":"12ed451084a39969"}},{"code_sha256_prefix":"f013f5243dee7c34","entry":"cat2psk","repo":"jacobyhsi/TabRep","repo_kind":"official","path":"tabrep_ddpm/models/gaussian_multinomial_distribution.py","file_url":"https://github.com/jacobyhsi/TabRep/blob/HEAD/tabrep_ddpm/models/gaussian_multinomial_distribution.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":"f013f5243dee7c34"}},{"code_sha256_prefix":"0730a0bcb1bd3048","entry":"convert_psk","repo":"jacobyhsi/TabRep","repo_kind":"official","path":"tabrep_flow/psk_utils.py","file_url":"https://github.com/jacobyhsi/TabRep/blob/HEAD/tabrep_flow/psk_utils.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":"0730a0bcb1bd3048"}},{"code_sha256_prefix":"3971992cf9c5dcfc","entry":"geglu","repo":"jacobyhsi/TabRep","repo_kind":"official","path":"tabrep_flow/models/modules.py","file_url":"https://github.com/jacobyhsi/TabRep/blob/HEAD/tabrep_flow/models/modules.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":"3971992cf9c5dcfc"}},{"code_sha256_prefix":"6aa6248e94eb7cb2","entry":"psk2cat","repo":"jacobyhsi/TabRep","repo_kind":"official","path":"tabrep_flow/psk_utils.py","file_url":"https://github.com/jacobyhsi/TabRep/blob/HEAD/tabrep_flow/psk_utils.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":"6aa6248e94eb7cb2"}},{"code_sha256_prefix":"0110658cf954b46a","entry":"recover_data","repo":"jacobyhsi/TabRep","repo_kind":"official","path":"tabrep_ddpm/sample.py","file_url":"https://github.com/jacobyhsi/TabRep/blob/HEAD/tabrep_ddpm/sample.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":"0110658cf954b46a"}},{"code_sha256_prefix":"7944b6aa2da08a07","entry":"reglu","repo":"jacobyhsi/TabRep","repo_kind":"official","path":"tabrep_flow/models/modules.py","file_url":"https://github.com/jacobyhsi/TabRep/blob/HEAD/tabrep_flow/models/modules.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":"7944b6aa2da08a07"}},{"code_sha256_prefix":"b5a210f358403b55","entry":"split_num_cat_target","repo":"jacobyhsi/TabRep","repo_kind":"official","path":"tabrep_ddpm/sample.py","file_url":"https://github.com/jacobyhsi/TabRep/blob/HEAD/tabrep_ddpm/sample.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":"b5a210f358403b55"}},{"code_sha256_prefix":"b1d5215baceb33a4","entry":"split_num_cat_target","repo":"jacobyhsi/TabRep","repo_kind":"official","path":"tabrep_flow/sample.py","file_url":"https://github.com/jacobyhsi/TabRep/blob/HEAD/tabrep_flow/sample.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":"b1d5215baceb33a4"}},{"code_sha256_prefix":"fe2398f0b08da143","entry":"timestep_embedding","repo":"jacobyhsi/TabRep","repo_kind":"official","path":"tabrep_ddpm/models/modules.py","file_url":"https://github.com/jacobyhsi/TabRep/blob/HEAD/tabrep_ddpm/models/modules.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":"fe2398f0b08da143"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}