{"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/fairness-without-demographics-through","title":"Fairness without Demographics through Adversarially Reweighted Learning","arxiv_id":"2006.13114","date":"2020-06-23","proceeding":"NeurIPS 2020 12","authors":["Preethi Lahoti","Alex Beutel","Jilin Chen","Kang Lee","Flavien Prost","Nithum Thain","Xuezhi Wang","Ed H. Chi"],"abstract":"Much of the previous machine learning (ML) fairness literature assumes that protected features such as race and sex are present in the dataset, and relies upon them to mitigate fairness concerns. However, in practice factors like privacy and regulation often preclude the collection of protected features, or their use for training or inference, severely limiting the applicability of traditional fairness research. Therefore we ask: How can we train an ML model to improve fairness when we do not even know the protected group memberships? In this work we address this problem by proposing Adversarially Reweighted Learning (ARL). In particular, we hypothesize that non-protected features and task labels are valuable for identifying fairness issues, and can be used to co-train an adversarial reweighting approach for improving fairness. Our results show that {ARL} improves Rawlsian Max-Min fairness, with notable AUC improvements for worst-case protected groups in multiple datasets, outperforming state-of-the-art alternatives.","url_abs":"https://arxiv.org/abs/2006.13114v3","url_pdf":"https://arxiv.org/pdf/2006.13114v3.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":"fairness-without-demographics-through","repo_url":"https://github.com/google-research/google-research/tree/master/group_agnostic_fairness","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null},{"paper_slug":"fairness-without-demographics-through","repo_url":"https://github.com/TinfoilHat0/BiFair","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"fairness-without-demographics-through","repo_url":"https://github.com/abbie0214/Fairness-without-Demographics-through-Adversarially-Reweighted-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"fairness-without-demographics-through","repo_url":"https://github.com/lucweytingh/ARL-UvA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"fairness-without-demographics-through","repo_url":"https://github.com/patrikken/fair-dsr/blob/main/src/ARL/arl.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"fairness","task_name":"Fairness"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2006.13114","atlas_url":"https://app.syntology.ai/?focus=2006.13114","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.13114"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/google-research/google-research","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TinfoilHat0/BiFair","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/patrikken/fair-dsr/blob/main/src/ARL/arl.py","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/google-research/tree/master/group_agnostic_fairness","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/abbie0214/Fairness-without-Demographics-through-Adversarially-Reweighted-Learning","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lucweytingh/ARL-UvA","reach":null}],"summary":{"ran":6,"unverified":2},"by_repo_kind":{"listed":{"samples":8,"ran":6,"repositories":2}},"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":"0edf6c65e388ca95","entry":"AdversaryNN","repo":"patrikken/fair-dsr","repo_kind":"listed","path":"src/ARL/arl.py","file_url":"https://github.com/patrikken/fair-dsr/blob/HEAD/src/ARL/arl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0edf6c65e388ca95"}},{"code_sha256_prefix":"7a3cb9ffdbc5d1f6","entry":"AdversaryNN","repo":"lucweytingh/ARL-UvA","repo_kind":"listed","path":"arl.py","file_url":"https://github.com/lucweytingh/ARL-UvA/blob/HEAD/arl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7a3cb9ffdbc5d1f6"}},{"code_sha256_prefix":"5d4863c2ec25fc37","entry":"DemParityMetric","repo":"patrikken/fair-dsr","repo_kind":"listed","path":"src/ARL/arl.py","file_url":"https://github.com/patrikken/fair-dsr/blob/HEAD/src/ARL/arl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5d4863c2ec25fc37"}},{"code_sha256_prefix":"cd3c47ac6974b37c","entry":"EqualOpportunity","repo":"patrikken/fair-dsr","repo_kind":"listed","path":"src/ARL/arl.py","file_url":"https://github.com/patrikken/fair-dsr/blob/HEAD/src/ARL/arl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cd3c47ac6974b37c"}},{"code_sha256_prefix":"75c30c9c6fb81781","entry":"EqualizedOdds","repo":"patrikken/fair-dsr","repo_kind":"listed","path":"src/ARL/arl.py","file_url":"https://github.com/patrikken/fair-dsr/blob/HEAD/src/ARL/arl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"75c30c9c6fb81781"}},{"code_sha256_prefix":"9f285e060e7712e1","entry":"LearnerNN","repo":"lucweytingh/ARL-UvA","repo_kind":"listed","path":"arl.py","file_url":"https://github.com/lucweytingh/ARL-UvA/blob/HEAD/arl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9f285e060e7712e1"}},{"code_sha256_prefix":"148bff5c92294183","entry":"ARL","repo":"patrikken/fair-dsr","repo_kind":"listed","path":"src/ARL/arl.py","file_url":"https://github.com/patrikken/fair-dsr/blob/HEAD/src/ARL/arl.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":"148bff5c92294183"}},{"code_sha256_prefix":"9dd8c5a15928b973","entry":"ARL","repo":"lucweytingh/ARL-UvA","repo_kind":"listed","path":"arl.py","file_url":"https://github.com/lucweytingh/ARL-UvA/blob/HEAD/arl.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":"9dd8c5a15928b973"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}