{"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/flexible-fairness-learning-via-inverse","title":"FairICP: Encouraging Equalized Odds via Inverse Conditional Permutation","arxiv_id":"2404.05678","date":"2024-04-08","proceeding":null,"authors":["Yuheng Lai","Leying Guan"],"abstract":"$\\textit{Equalized odds}$, an important notion of algorithmic fairness, aims to ensure that sensitive variables, such as race and gender, do not unfairly influence the algorithm's prediction when conditioning on the true outcome. Despite rapid advancements, current research primarily focuses on equalized odds violations caused by a single sensitive attribute, leaving the challenge of simultaneously accounting for multiple attributes under-addressed. We bridge this gap by introducing an in-processing fairness-aware learning approach, FairICP, which integrates adversarial learning with a novel inverse conditional permutation scheme. FairICP offers a flexible and efficient scheme to promote equalized odds under fairness conditions described by complex and multi-dimensional sensitive attributes. The efficacy and adaptability of our method are demonstrated through both simulation studies and empirical analyses of real-world datasets.","url_abs":"https://arxiv.org/abs/2404.05678v4","url_pdf":"https://arxiv.org/pdf/2404.05678v4.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":"flexible-fairness-learning-via-inverse","repo_url":"https://github.com/yuhenglai/fairicp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"fairness","task_name":"Fairness"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.05678","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05678"}},"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/yuhenglai/fairicp","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":6},"by_repo_kind":{"official":{"samples":7,"ran":1,"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":"6ccd7b1944124a17","entry":"inner_train_model_regression","repo":"yuhenglai/fairicp","repo_kind":"official","path":"FairICP/FairICP_learning.py","file_url":"https://github.com/yuhenglai/fairicp/blob/HEAD/FairICP/FairICP_learning.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":"6ccd7b1944124a17"}},{"code_sha256_prefix":"883fbb83d5ae1975","entry":"get_adult","repo":"yuhenglai/fairicp","repo_kind":"official","path":"get_dataset.py","file_url":"https://github.com/yuhenglai/fairicp/blob/HEAD/get_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":"883fbb83d5ae1975"}},{"code_sha256_prefix":"2ccd35988d2af964","entry":"inner_train_adversary_regression","repo":"yuhenglai/fairicp","repo_kind":"official","path":"FairICP/FairICP_learning.py","file_url":"https://github.com/yuhenglai/fairicp/blob/HEAD/FairICP/FairICP_learning.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":"2ccd35988d2af964"}},{"code_sha256_prefix":"0f349fab20f391df","entry":"make_bijector_kwargs","repo":"yuhenglai/fairicp","repo_kind":"official","path":"FairICP/utility_functions.py","file_url":"https://github.com/yuhenglai/fairicp/blob/HEAD/FairICP/utility_functions.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":"0f349fab20f391df"}},{"code_sha256_prefix":"86d960d03febca04","entry":"read_compas_data_df","repo":"yuhenglai/fairicp","repo_kind":"official","path":"get_dataset.py","file_url":"https://github.com/yuhenglai/fairicp/blob/HEAD/get_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":"86d960d03febca04"}},{"code_sha256_prefix":"e2b93449bcd416bb","entry":"read_crimes_data_df","repo":"yuhenglai/fairicp","repo_kind":"official","path":"get_dataset.py","file_url":"https://github.com/yuhenglai/fairicp/blob/HEAD/get_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":"e2b93449bcd416bb"}},{"code_sha256_prefix":"603a07757f23713b","entry":"train_classifier","repo":"yuhenglai/fairicp","repo_kind":"official","path":"FairICP/FairICP_learning.py","file_url":"https://github.com/yuhenglai/fairicp/blob/HEAD/FairICP/FairICP_learning.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":"603a07757f23713b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}