{"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/rethinking-bias-mitigation-fairer","title":"Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition","arxiv_id":"2210.09943","date":"2022-10-18","proceeding":"NeurIPS 2023 11","authors":["Samuel Dooley","Rhea Sanjay Sukthanker","John P. Dickerson","Colin White","Frank Hutter","Micah Goldblum"],"abstract":"Face recognition systems are widely deployed in safety-critical applications, including law enforcement, yet they exhibit bias across a range of socio-demographic dimensions, such as gender and race. Conventional wisdom dictates that model biases arise from biased training data. As a consequence, previous works on bias mitigation largely focused on pre-processing the training data, adding penalties to prevent bias from effecting the model during training, or post-processing predictions to debias them, yet these approaches have shown limited success on hard problems such as face recognition. In our work, we discover that biases are actually inherent to neural network architectures themselves. Following this reframing, we conduct the first neural architecture search for fairness, jointly with a search for hyperparameters. Our search outputs a suite of models which Pareto-dominate all other high-performance architectures and existing bias mitigation methods in terms of accuracy and fairness, often by large margins, on the two most widely used datasets for face identification, CelebA and VGGFace2. Furthermore, these models generalize to other datasets and sensitive attributes. We release our code, models and raw data files at https://github.com/dooleys/FR-NAS.","url_abs":"https://arxiv.org/abs/2210.09943v3","url_pdf":"https://arxiv.org/pdf/2210.09943v3.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":"rethinking-bias-mitigation-fairer","repo_url":"https://github.com/dooleys/fr-nas","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"rethinking-bias-mitigation-fairer","repo_url":"https://github.com/FaceOnLive/Face-Recognition-SDK-Android","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"face-identification","task_name":"Face Identification"},{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"fairness","task_name":"Fairness"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.09943","atlas_url":"https://app.syntology.ai/?focus=2210.09943","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.09943"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/FaceOnLive/Face-Recognition-SDK-Android","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dooleys/fr-nas","reach":null}],"summary":{"ran_honours":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"7695938f46a5f5b1","entry":"stat_parity_func","repo":"dooleys/fr-nas","repo_kind":"official","path":"analysis/analysis.py","file_url":"https://github.com/dooleys/fr-nas/blob/HEAD/analysis/analysis.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7695938f46a5f5b1"}},{"code_sha256_prefix":"a7d51f30b1427717","entry":"stat_parity_rank_func","repo":"dooleys/fr-nas","repo_kind":"official","path":"analysis/analysis.py","file_url":"https://github.com/dooleys/fr-nas/blob/HEAD/analysis/analysis.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a7d51f30b1427717"}},{"code_sha256_prefix":"1f72eeb951d27500","entry":"stat_parity_ratio_func","repo":"dooleys/fr-nas","repo_kind":"official","path":"analysis/analysis.py","file_url":"https://github.com/dooleys/fr-nas/blob/HEAD/analysis/analysis.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1f72eeb951d27500"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}