{"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/disparate-impact-on-group-accuracy-of","title":"Disparate Impact on Group Accuracy of Linearization for Private Inference","arxiv_id":"2402.03629","date":"2024-02-06","proceeding":null,"authors":["Saswat Das","Marco Romanelli","Ferdinando Fioretto"],"abstract":"Ensuring privacy-preserving inference on cryptographically secure data is a well-known computational challenge. To alleviate the bottleneck of costly cryptographic computations in non-linear activations, recent methods have suggested linearizing a targeted portion of these activations in neural networks. This technique results in significantly reduced runtimes with often negligible impacts on accuracy. In this paper, we demonstrate that such computational benefits may lead to increased fairness costs. Specifically, we find that reducing the number of ReLU activations disproportionately decreases the accuracy for minority groups compared to majority groups. To explain these observations, we provide a mathematical interpretation under restricted assumptions about the nature of the decision boundary, while also showing the prevalence of this problem across widely used datasets and architectures. Finally, we show how a simple procedure altering the fine-tuning step for linearized models can serve as an effective mitigation strategy.","url_abs":"https://arxiv.org/abs/2402.03629v3","url_pdf":"https://arxiv.org/pdf/2402.03629v3.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":"disparate-impact-on-group-accuracy-of","repo_url":"https://github.com/saswatd27/icml_linearization_disparate_impact","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"fairness","task_name":"Fairness"},{"task_slug":"privacy-preserving","task_name":"Privacy Preserving"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2402.03629","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03629"}},"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/saswatd27/icml_linearization_disparate_impact","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"b4796720b7a7685d","entry":"relu_counting","repo":"saswatd27/icml_linearization_disparate_impact","repo_kind":"official","path":"SNLCode/snl_finetune_mitigate.py","file_url":"https://github.com/saswatd27/icml_linearization_disparate_impact/blob/HEAD/SNLCode/snl_finetune_mitigate.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":"b4796720b7a7685d"}},{"code_sha256_prefix":"e43301552f93b954","entry":"reshape_and_create_loader","repo":"saswatd27/icml_linearization_disparate_impact","repo_kind":"official","path":"DeepReduce/runDeepReduce_mitigate.py","file_url":"https://github.com/saswatd27/icml_linearization_disparate_impact/blob/HEAD/DeepReduce/runDeepReduce_mitigate.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e43301552f93b954"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}