{"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/gain-missing-data-imputation-using-generative","title":"GAIN: Missing Data Imputation using Generative Adversarial Nets","arxiv_id":"1806.02920","date":"2018-06-07","proceeding":"ICML 2018 7","authors":["Jinsung Yoon","James Jordon","Mihaela van der Schaar"],"abstract":"We propose a novel method for imputing missing data by adapting the\nwell-known Generative Adversarial Nets (GAN) framework. Accordingly, we call\nour method Generative Adversarial Imputation Nets (GAIN). The generator (G)\nobserves some components of a real data vector, imputes the missing components\nconditioned on what is actually observed, and outputs a completed vector. The\ndiscriminator (D) then takes a completed vector and attempts to determine which\ncomponents were actually observed and which were imputed. To ensure that D\nforces G to learn the desired distribution, we provide D with some additional\ninformation in the form of a hint vector. The hint reveals to D partial\ninformation about the missingness of the original sample, which is used by D to\nfocus its attention on the imputation quality of particular components. This\nhint ensures that G does in fact learn to generate according to the true data\ndistribution. We tested our method on various datasets and found that GAIN\nsignificantly outperforms state-of-the-art imputation methods.","url_abs":"http://arxiv.org/abs/1806.02920v1","url_pdf":"http://arxiv.org/pdf/1806.02920v1.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":"gain-missing-data-imputation-using-generative","repo_url":"https://github.com/jsyoon0823/GAIN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"gain-missing-data-imputation-using-generative","repo_url":"https://github.com/CKPOON0619/GAIN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"gain-missing-data-imputation-using-generative","repo_url":"https://github.com/dzerkes/GAIN---Deep-Learning-Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"gain-missing-data-imputation-using-generative","repo_url":"https://github.com/evolext/GAIN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"gain-missing-data-imputation-using-generative","repo_url":"https://github.com/purbayankar/Advanced_GAIN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"gain-missing-data-imputation-using-generative","repo_url":"https://github.com/vanderschaarlab/autoprognosis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"gain-missing-data-imputation-using-generative","repo_url":"https://github.com/dhanajitb/GAIN-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"gain-missing-data-imputation-using-generative","repo_url":"https://github.com/javiersgjavi/GAIN-Pytorch-Lightning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"imputation","task_name":"Imputation"},{"task_slug":"multivariate-time-series-imputation","task_name":"Multivariate Time Series Imputation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multivariate-time-series-imputation-on-kdd","task":"Multivariate Time Series Imputation","dataset":"KDD CUP Challenge 2018","model":"GAIN","rank_in_archive_order":3,"of":4,"metrics":{"MSE (10% missing)":"0.378"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.02920","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.02920"}},"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/dhanajitb/GAIN-Pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dzerkes/GAIN---Deep-Learning-Project","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/javiersgjavi/GAIN-Pytorch-Lightning","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/purbayankar/Advanced_GAIN","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/evolext/GAIN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jsyoon0823/GAIN","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/CKPOON0619/GAIN","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vanderschaarlab/autoprognosis","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"ran":1,"unverified":6},"by_repo_kind":{"listed":{"samples":8,"ran":2,"repositories":3}},"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":1,"samples":[{"code_sha256_prefix":"a8f2fc3e489a4f0b","entry":"add_missings","repo":"evolext/GAIN","repo_kind":"listed","path":"usage_example.py","file_url":"https://github.com/evolext/GAIN/blob/HEAD/usage_example.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a8f2fc3e489a4f0b"}},{"code_sha256_prefix":"4c35427d43331cd0","entry":"create_log_and_print_function","repo":"vanderschaarlab/autoprognosis","repo_kind":"listed","path":"src/autoprognosis/logger.py","file_url":"https://github.com/vanderschaarlab/autoprognosis/blob/HEAD/src/autoprognosis/logger.py","link_basis":"harvester_set","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":"4c35427d43331cd0"}},{"code_sha256_prefix":"3f19c5bd16fdbc0c","entry":"file_md5","repo":"vanderschaarlab/autoprognosis","repo_kind":"listed","path":"src/autoprognosis/deploy/utils.py","file_url":"https://github.com/vanderschaarlab/autoprognosis/blob/HEAD/src/autoprognosis/deploy/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3f19c5bd16fdbc0c"}},{"code_sha256_prefix":"20da4d2fa83c9ca0","entry":"generate_missing_mask","repo":"javiersgjavi/GAIN-Pytorch-Lightning","repo_kind":"listed","path":"src/utils.py","file_url":"https://github.com/javiersgjavi/GAIN-Pytorch-Lightning/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"20da4d2fa83c9ca0"}},{"code_sha256_prefix":"03d93bad5a276b63","entry":"get_ports","repo":"vanderschaarlab/autoprognosis","repo_kind":"listed","path":"src/autoprognosis/deploy/utils.py","file_url":"https://github.com/vanderschaarlab/autoprognosis/blob/HEAD/src/autoprognosis/deploy/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"03d93bad5a276b63"}},{"code_sha256_prefix":"e4a86ddf71deb01a","entry":"is_local_port_open","repo":"vanderschaarlab/autoprognosis","repo_kind":"listed","path":"src/autoprognosis/deploy/utils.py","file_url":"https://github.com/vanderschaarlab/autoprognosis/blob/HEAD/src/autoprognosis/deploy/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e4a86ddf71deb01a"}},{"code_sha256_prefix":"41e8673c5a47185d","entry":"loss_d","repo":"javiersgjavi/GAIN-Pytorch-Lightning","repo_kind":"listed","path":"src/utils.py","file_url":"https://github.com/javiersgjavi/GAIN-Pytorch-Lightning/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"41e8673c5a47185d"}},{"code_sha256_prefix":"0193c5aa7f5a1eae","entry":"loss_g","repo":"javiersgjavi/GAIN-Pytorch-Lightning","repo_kind":"listed","path":"src/utils.py","file_url":"https://github.com/javiersgjavi/GAIN-Pytorch-Lightning/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0193c5aa7f5a1eae"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}