{"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/simon-says-evaluating-and-mitigating-bias-in","title":"Simon Says: Evaluating and Mitigating Bias in Pruned Neural Networks with Knowledge Distillation","arxiv_id":"2106.07849","date":"2021-06-15","proceeding":null,"authors":["Cody Blakeney","Nathaniel Huish","Yan Yan","Ziliang Zong"],"abstract":"In recent years the ubiquitous deployment of AI has posed great concerns in regards to algorithmic bias, discrimination, and fairness. Compared to traditional forms of bias or discrimination caused by humans, algorithmic bias generated by AI is more abstract and unintuitive therefore more difficult to explain and mitigate. A clear gap exists in the current literature on evaluating and mitigating bias in pruned neural networks. In this work, we strive to tackle the challenging issues of evaluating, mitigating, and explaining induced bias in pruned neural networks. Our paper makes three contributions. First, we propose two simple yet effective metrics, Combined Error Variance (CEV) and Symmetric Distance Error (SDE), to quantitatively evaluate the induced bias prevention quality of pruned models. Second, we demonstrate that knowledge distillation can mitigate induced bias in pruned neural networks, even with unbalanced datasets. Third, we reveal that model similarity has strong correlations with pruning induced bias, which provides a powerful method to explain why bias occurs in pruned neural networks. Our code is available at https://github.com/codestar12/pruning-distilation-bias","url_abs":"https://arxiv.org/abs/2106.07849v1","url_pdf":"https://arxiv.org/pdf/2106.07849v1.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":"simon-says-evaluating-and-mitigating-bias-in","repo_url":"https://github.com/codestar12/pruning-distilation-bias","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"tasks":[{"task_slug":"fairness","task_name":"Fairness"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"},{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.07849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.07849"}},"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/codestar12/pruning-distilation-bias","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"summary":{"ran_draft_wrong":2,"ran":2,"unverified":3},"by_repo_kind":{"official":{"samples":7,"ran":4,"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":"fac5364e2f53c6db","entry":"conv3x3","repo":"codestar12/pruning-distilation-bias","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/codestar12/pruning-distilation-bias/blob/HEAD/models/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"7765583b9e540679","entry":"conv_1x1_bn","repo":"codestar12/pruning-distilation-bias","repo_kind":"official","path":"models/mobilenetv2.py","file_url":"https://github.com/codestar12/pruning-distilation-bias/blob/HEAD/models/mobilenetv2.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"7765583b9e540679"}},{"code_sha256_prefix":"2f7853ff01cbbc29","entry":"conv_bn","repo":"codestar12/pruning-distilation-bias","repo_kind":"official","path":"models/mobilenetv2.py","file_url":"https://github.com/codestar12/pruning-distilation-bias/blob/HEAD/models/mobilenetv2.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2f7853ff01cbbc29"}},{"code_sha256_prefix":"421fd14c036bc279","entry":"mobilenetv2_T_w","repo":"codestar12/pruning-distilation-bias","repo_kind":"official","path":"models/mobilenetv2.py","file_url":"https://github.com/codestar12/pruning-distilation-bias/blob/HEAD/models/mobilenetv2.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"421fd14c036bc279"}},{"code_sha256_prefix":"f72c2cd04bab2cce","entry":"get_dataloader_sample","repo":"codestar12/pruning-distilation-bias","repo_kind":"official","path":"dataset/imagenet.py","file_url":"https://github.com/codestar12/pruning-distilation-bias/blob/HEAD/dataset/imagenet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"f72c2cd04bab2cce"}},{"code_sha256_prefix":"766301706c702922","entry":"get_imagenet_dataloader","repo":"codestar12/pruning-distilation-bias","repo_kind":"official","path":"dataset/imagenet.py","file_url":"https://github.com/codestar12/pruning-distilation-bias/blob/HEAD/dataset/imagenet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"766301706c702922"}},{"code_sha256_prefix":"91b1735890dcfa99","entry":"get_test_loader","repo":"codestar12/pruning-distilation-bias","repo_kind":"official","path":"dataset/imagenet.py","file_url":"https://github.com/codestar12/pruning-distilation-bias/blob/HEAD/dataset/imagenet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"91b1735890dcfa99"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}