{"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/learning-robust-classifiers-with-self-guided","title":"Learning Robust Classifiers with Self-Guided Spurious Correlation Mitigation","arxiv_id":"2405.03649","date":"2024-05-06","proceeding":null,"authors":["Guangtao Zheng","Wenqian Ye","Aidong Zhang"],"abstract":"Deep neural classifiers tend to rely on spurious correlations between spurious attributes of inputs and targets to make predictions, which could jeopardize their generalization capability. Training classifiers robust to spurious correlations typically relies on annotations of spurious correlations in data, which are often expensive to get. In this paper, we tackle an annotation-free setting and propose a self-guided spurious correlation mitigation framework. Our framework automatically constructs fine-grained training labels tailored for a classifier obtained with empirical risk minimization to improve its robustness against spurious correlations. The fine-grained training labels are formulated with different prediction behaviors of the classifier identified in a novel spuriousness embedding space. We construct the space with automatically detected conceptual attributes and a novel spuriousness metric which measures how likely a class-attribute correlation is exploited for predictions. We demonstrate that training the classifier to distinguish different prediction behaviors reduces its reliance on spurious correlations without knowing them a priori and outperforms prior methods on five real-world datasets.","url_abs":"https://arxiv.org/abs/2405.03649v1","url_pdf":"https://arxiv.org/pdf/2405.03649v1.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":"learning-robust-classifiers-with-self-guided","repo_url":"https://github.com/gtzheng/LBC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.03649","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.03649"}},"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/gtzheng/LBC","reach":{"status":"ok"}}],"summary":{"ran":7,"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"official":{"samples":11,"ran":10,"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":11,"samples":[{"code_sha256_prefix":"081ace50b2afb20c","entry":"collect_dataset_info","repo":"gtzheng/LBC","repo_kind":"official","path":"datasets/in9_data.py","file_url":"https://github.com/gtzheng/LBC/blob/HEAD/datasets/in9_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"081ace50b2afb20c"}},{"code_sha256_prefix":"d9def42110729a85","entry":"conv1x1","repo":"gtzheng/LBC","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/gtzheng/LBC/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d9def42110729a85"}},{"code_sha256_prefix":"160bb14bd76201b4","entry":"conv3x3","repo":"gtzheng/LBC","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/gtzheng/LBC/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"160bb14bd76201b4"}},{"code_sha256_prefix":"0ea0c32c88e93404","entry":"find_classes","repo":"gtzheng/LBC","repo_kind":"official","path":"datasets/in9_data.py","file_url":"https://github.com/gtzheng/LBC/blob/HEAD/datasets/in9_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0ea0c32c88e93404"}},{"code_sha256_prefix":"511d5c5ed80c997c","entry":"get_correlated_features","repo":"gtzheng/LBC","repo_kind":"official","path":"lbc_train.py","file_url":"https://github.com/gtzheng/LBC/blob/HEAD/lbc_train.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"511d5c5ed80c997c"}},{"code_sha256_prefix":"99b2feaf01dd4f13","entry":"get_transform_biased","repo":"gtzheng/LBC","repo_kind":"official","path":"datasets/wb_data.py","file_url":"https://github.com/gtzheng/LBC/blob/HEAD/datasets/wb_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"99b2feaf01dd4f13"}},{"code_sha256_prefix":"45146ddac421def6","entry":"get_transform_in","repo":"gtzheng/LBC","repo_kind":"official","path":"datasets/inA_data.py","file_url":"https://github.com/gtzheng/LBC/blob/HEAD/datasets/inA_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"45146ddac421def6"}},{"code_sha256_prefix":"d66f024e276fe9b2","entry":"get_transform_nico","repo":"gtzheng/LBC","repo_kind":"official","path":"datasets/nico_data.py","file_url":"https://github.com/gtzheng/LBC/blob/HEAD/datasets/nico_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d66f024e276fe9b2"}},{"code_sha256_prefix":"9c67275dc5e1daaf","entry":"is_image_file","repo":"gtzheng/LBC","repo_kind":"official","path":"datasets/in9_data.py","file_url":"https://github.com/gtzheng/LBC/blob/HEAD/datasets/in9_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9c67275dc5e1daaf"}},{"code_sha256_prefix":"df8ef801f1f069b0","entry":"time_str","repo":"gtzheng/LBC","repo_kind":"official","path":"utils.py","file_url":"https://github.com/gtzheng/LBC/blob/HEAD/utils.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"df8ef801f1f069b0"}},{"code_sha256_prefix":"3121390d86a16776","entry":"resnet18","repo":"gtzheng/LBC","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/gtzheng/LBC/blob/HEAD/models/resnet.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":"3121390d86a16776"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}