{"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/post-hoc-methods-for-debiasing-neural","title":"Intra-Processing Methods for Debiasing Neural Networks","arxiv_id":"2006.08564","date":"2020-06-15","proceeding":"NeurIPS 2020 12","authors":["Yash Savani","Colin White","Naveen Sundar Govindarajulu"],"abstract":"As deep learning models become tasked with more and more decisions that impact human lives, such as criminal recidivism, loan repayment, and face recognition for law enforcement, bias is becoming a growing concern. Debiasing algorithms are typically split into three paradigms: pre-processing, in-processing, and post-processing. However, in computer vision or natural language applications, it is common to start with a large generic model and then fine-tune to a specific use-case. Pre- or in-processing methods would require retraining the entire model from scratch, while post-processing methods only have black-box access to the model, so they do not leverage the weights of the trained model. Creating debiasing algorithms specifically for this fine-tuning use-case has largely been neglected. In this work, we initiate the study of a new paradigm in debiasing research, intra-processing, which sits between in-processing and post-processing methods. Intra-processing methods are designed specifically to debias large models which have been trained on a generic dataset and fine-tuned on a more specific task. We show how to repurpose existing in-processing methods for this use-case, and we also propose three baseline algorithms: random perturbation, layerwise optimization, and adversarial fine-tuning. All of our techniques can be used for all popular group fairness measures such as equalized odds or statistical parity difference. We evaluate these methods across three popular datasets from the AIF360 toolkit, as well as on the CelebA faces dataset. Our code is available at https://github.com/abacusai/intraprocessing_debiasing.","url_abs":"https://arxiv.org/abs/2006.08564v2","url_pdf":"https://arxiv.org/pdf/2006.08564v2.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":"post-hoc-methods-for-debiasing-neural","repo_url":"https://github.com/abacusai/intraprocessing_debiasing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"post-hoc-methods-for-debiasing-neural","repo_url":"https://github.com/realityengines/post_hoc_debiasing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"post-hoc-methods-for-debiasing-neural","repo_url":"https://github.com/FairUnlearn/detoxai","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"post-hoc-methods-for-debiasing-neural","repo_url":"https://github.com/i6092467/diff-bias-proxies","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"fairness","task_name":"Fairness"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.08564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.08564"}},"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/realityengines/post_hoc_debiasing","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/FairUnlearn/detoxai","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/abacusai/intraprocessing_debiasing","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/i6092467/diff-bias-proxies","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":3,"ran_honours":2},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":"53d8bc44e5112bfb","entry":"compute_bias","repo":"realityengines/post_hoc_debiasing","repo_kind":"official","path":"post_hoc_lib.py","file_url":"https://github.com/realityengines/post_hoc_debiasing/blob/HEAD/post_hoc_lib.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"53d8bc44e5112bfb"}},{"code_sha256_prefix":"aa041e2ad3437517","entry":"compute_bias","repo":"abacusai/intraprocessing_debiasing","repo_kind":"official","path":"intraproc_celeba.py","file_url":"https://github.com/abacusai/intraprocessing_debiasing/blob/HEAD/intraproc_celeba.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aa041e2ad3437517"}},{"code_sha256_prefix":"d3368b0f34abf978","entry":"get_best_accuracy","repo":"realityengines/post_hoc_debiasing","repo_kind":"official","path":"post_hoc_lib.py","file_url":"https://github.com/realityengines/post_hoc_debiasing/blob/HEAD/post_hoc_lib.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d3368b0f34abf978"}},{"code_sha256_prefix":"96d2e5b01c6f59f9","entry":"val_model","repo":"realityengines/post_hoc_debiasing","repo_kind":"official","path":"post_hoc_lib.py","file_url":"https://github.com/realityengines/post_hoc_debiasing/blob/HEAD/post_hoc_lib.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"96d2e5b01c6f59f9"}},{"code_sha256_prefix":"dd4f64a67087a214","entry":"val_model","repo":"abacusai/intraprocessing_debiasing","repo_kind":"official","path":"intraproc_celeba.py","file_url":"https://github.com/abacusai/intraprocessing_debiasing/blob/HEAD/intraproc_celeba.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dd4f64a67087a214"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}