{"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/scalable-penalized-regression-for-noise","title":"Scalable Penalized Regression for Noise Detection in Learning with Noisy Labels","arxiv_id":"2203.07788","date":"2022-03-15","proceeding":"CVPR 2022 1","authors":["Yikai Wang","Xinwei Sun","Yanwei Fu"],"abstract":"Noisy training set usually leads to the degradation of generalization and robustness of neural networks. In this paper, we propose using a theoretically guaranteed noisy label detection framework to detect and remove noisy data for Learning with Noisy Labels (LNL). Specifically, we design a penalized regression to model the linear relation between network features and one-hot labels, where the noisy data are identified by the non-zero mean shift parameters solved in the regression model. To make the framework scalable to datasets that contain a large number of categories and training data, we propose a split algorithm to divide the whole training set into small pieces that can be solved by the penalized regression in parallel, leading to the Scalable Penalized Regression (SPR) framework. We provide the non-asymptotic probabilistic condition for SPR to correctly identify the noisy data. While SPR can be regarded as a sample selection module for standard supervised training pipeline, we further combine it with semi-supervised algorithm to further exploit the support of noisy data as unlabeled data. Experimental results on several benchmark datasets and real-world noisy datasets show the effectiveness of our framework. Our code and pretrained models are released at https://github.com/Yikai-Wang/SPR-LNL.","url_abs":"https://arxiv.org/abs/2203.07788v2","url_pdf":"https://arxiv.org/pdf/2203.07788v2.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":"scalable-penalized-regression-for-noise","repo_url":"https://github.com/yikai-wang/spr-lnl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"learning-with-noisy-labels","task_name":"Learning with noisy labels"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-clothing1m","task":"Image Classification","dataset":"Clothing1M","model":"SPR","rank_in_archive_order":42,"of":51,"metrics":{"Accuracy":"71.16%"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-animal","task":"Learning with noisy labels","dataset":"ANIMAL","model":"SPR","rank_in_archive_order":7,"of":19,"metrics":{"Accuracy":"86.8","ImageNet Pretrained":"NO","Network":"VGG19-BN"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-clothing1m","task":"Learning with noisy labels","dataset":"Clothing1M","model":"SPR","rank_in_archive_order":5,"of":5,"metrics":{"Test Accuracy":"71.16"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.07788","atlas_url":"https://app.syntology.ai/?focus=2203.07788","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.07788"}},"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/yikai-wang/spr-lnl","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Yikai-Wang/SPR-LNL","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"b215cd24009a0d36","entry":"get_one_hot","repo":"Yikai-Wang/SPR-LNL","repo_kind":"official","path":"models/spr.py","file_url":"https://github.com/Yikai-Wang/SPR-LNL/blob/HEAD/models/spr.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b215cd24009a0d36"}},{"code_sha256_prefix":"5c4e1ae7d5028584","entry":"linear","repo":"Yikai-Wang/SPR-LNL","repo_kind":"official","path":"models/spr.py","file_url":"https://github.com/Yikai-Wang/SPR-LNL/blob/HEAD/models/spr.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5c4e1ae7d5028584"}},{"code_sha256_prefix":"292076f83e037499","entry":"spr","repo":"Yikai-Wang/SPR-LNL","repo_kind":"official","path":"models/spr.py","file_url":"https://github.com/Yikai-Wang/SPR-LNL/blob/HEAD/models/spr.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"292076f83e037499"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}