{"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/differentially-private-mixed-type-data-1","title":"Differentially Private Synthetic Mixed-Type Data Generation For Unsupervised Learning","arxiv_id":"1912.03250","date":"2019-12-06","proceeding":null,"authors":["Uthaipon Tantipongpipat","Chris Waites","Digvijay Boob","Amaresh Ankit Siva","Rachel Cummings"],"abstract":"We introduce the DP-auto-GAN framework for synthetic data generation, which combines the low dimensional representation of autoencoders with the flexibility of Generative Adversarial Networks (GANs). This framework can be used to take in raw sensitive data and privately train a model for generating synthetic data that will satisfy similar statistical properties as the original data. This learned model can generate an arbitrary amount of synthetic data, which can then be freely shared due to the post-processing guarantee of differential privacy. Our framework is applicable to unlabeled mixed-type data, that may include binary, categorical, and real-valued data. We implement this framework on both binary data (MIMIC-III) and mixed-type data (ADULT), and compare its performance with existing private algorithms on metrics in unsupervised settings. We also introduce a new quantitative metric able to detect diversity, or lack thereof, of synthetic data.","url_abs":"https://arxiv.org/abs/1912.03250v2","url_pdf":"https://arxiv.org/pdf/1912.03250v2.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":"differentially-private-mixed-type-data-1","repo_url":"https://github.com/DPautoGAN/DPautoGAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"synthetic-data-generation","task_name":"Synthetic Data Generation"},{"task_slug":"type","task_name":"Vocal Bursts Type Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1912.03250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.03250"}},"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/DPautoGAN/DPautoGAN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"unverified":9},"by_repo_kind":{"official":{"samples":11,"ran":2,"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":"9f1a1575f6901240","entry":"convert_to_3digit_icd9","repo":"DPautoGAN/DPautoGAN","repo_kind":"official","path":"mimic/mimic_dataset.py","file_url":"https://github.com/DPautoGAN/DPautoGAN/blob/HEAD/mimic/mimic_dataset.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9f1a1575f6901240"}},{"code_sha256_prefix":"f782bcdaf42568da","entry":"convert_to_icd9","repo":"DPautoGAN/DPautoGAN","repo_kind":"official","path":"mimic/mimic_dataset.py","file_url":"https://github.com/DPautoGAN/DPautoGAN/blob/HEAD/mimic/mimic_dataset.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f782bcdaf42568da"}},{"code_sha256_prefix":"f3c0636a6c2e8bf2","entry":"balance","repo":"DPautoGAN/DPautoGAN","repo_kind":"official","path":"mimic/evaluation.py","file_url":"https://github.com/DPautoGAN/DPautoGAN/blob/HEAD/mimic/evaluation.py","link_basis":"first_harvest_node","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":"f3c0636a6c2e8bf2"}},{"code_sha256_prefix":"dfcf05f8070a1a7d","entry":"compute_rdp","repo":"DPautoGAN/DPautoGAN","repo_kind":"official","path":"mimic/rdp_accountant.py","file_url":"https://github.com/DPautoGAN/DPautoGAN/blob/HEAD/mimic/rdp_accountant.py","link_basis":"first_harvest_node","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":"dfcf05f8070a1a7d"}},{"code_sha256_prefix":"1bd33e484e06a1e7","entry":"compute_rdp_from_ledger","repo":"DPautoGAN/DPautoGAN","repo_kind":"official","path":"mimic/rdp_accountant.py","file_url":"https://github.com/DPautoGAN/DPautoGAN/blob/HEAD/mimic/rdp_accountant.py","link_basis":"first_harvest_node","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":"1bd33e484e06a1e7"}},{"code_sha256_prefix":"d18aa2d6a3614265","entry":"get_data_loaders","repo":"DPautoGAN/DPautoGAN","repo_kind":"official","path":"mimic/sampling.py","file_url":"https://github.com/DPautoGAN/DPautoGAN/blob/HEAD/mimic/sampling.py","link_basis":"first_harvest_node","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":"d18aa2d6a3614265"}},{"code_sha256_prefix":"cb6574d99c975563","entry":"get_patient_matrix","repo":"DPautoGAN/DPautoGAN","repo_kind":"official","path":"mimic/mimic_dataset.py","file_url":"https://github.com/DPautoGAN/DPautoGAN/blob/HEAD/mimic/mimic_dataset.py","link_basis":"first_harvest_node","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":"cb6574d99c975563"}},{"code_sha256_prefix":"8d151a57c7d4a1bf","entry":"get_prediction_score","repo":"DPautoGAN/DPautoGAN","repo_kind":"official","path":"mimic/evaluation.py","file_url":"https://github.com/DPautoGAN/DPautoGAN/blob/HEAD/mimic/evaluation.py","link_basis":"first_harvest_node","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":"8d151a57c7d4a1bf"}},{"code_sha256_prefix":"690416000476a525","entry":"get_privacy_spent","repo":"DPautoGAN/DPautoGAN","repo_kind":"official","path":"mimic/rdp_accountant.py","file_url":"https://github.com/DPautoGAN/DPautoGAN/blob/HEAD/mimic/rdp_accountant.py","link_basis":"first_harvest_node","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":"690416000476a525"}},{"code_sha256_prefix":"18e3ea94db9eb751","entry":"isolate_column","repo":"DPautoGAN/DPautoGAN","repo_kind":"official","path":"mimic/evaluation.py","file_url":"https://github.com/DPautoGAN/DPautoGAN/blob/HEAD/mimic/evaluation.py","link_basis":"first_harvest_node","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":"18e3ea94db9eb751"}},{"code_sha256_prefix":"02dc1abf1033d768","entry":"make_optimizer_class","repo":"DPautoGAN/DPautoGAN","repo_kind":"official","path":"mimic/dp_optimizer.py","file_url":"https://github.com/DPautoGAN/DPautoGAN/blob/HEAD/mimic/dp_optimizer.py","link_basis":"first_harvest_node","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":"02dc1abf1033d768"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}