{"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/complexity-matters-dynamics-of-feature","title":"Complexity Matters: Dynamics of Feature Learning in the Presence of Spurious Correlations","arxiv_id":"2403.03375","date":"2024-03-05","proceeding":null,"authors":["Guanwen Qiu","Da Kuang","Surbhi Goel"],"abstract":"Existing research often posits spurious features as easier to learn than core features in neural network optimization, but the impact of their relative simplicity remains under-explored. Moreover, studies mainly focus on end performance rather than the learning dynamics of feature learning. In this paper, we propose a theoretical framework and an associated synthetic dataset grounded in boolean function analysis. This setup allows for fine-grained control over the relative complexity (compared to core features) and correlation strength (with respect to the label) of spurious features to study the dynamics of feature learning under spurious correlations. Our findings uncover several interesting phenomena: (1) stronger spurious correlations or simpler spurious features slow down the learning rate of the core features, (2) two distinct subnetworks are formed to learn core and spurious features separately, (3) learning phases of spurious and core features are not always separable, (4) spurious features are not forgotten even after core features are fully learned. We demonstrate that our findings justify the success of retraining the last layer to remove spurious correlation and also identifies limitations of popular debiasing algorithms that exploit early learning of spurious features. We support our empirical findings with theoretical analyses for the case of learning XOR features with a one-hidden-layer ReLU network.","url_abs":"https://arxiv.org/abs/2403.03375v3","url_pdf":"https://arxiv.org/pdf/2403.03375v3.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":"complexity-matters-dynamics-of-feature","repo_url":"https://github.com/NayutaQiu/Boolean_Spurious","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[{"slug":"spurious-boolean-dataset","name":"Spurious Boolean Dataset","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.03375","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03375"}},"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/NayutaQiu/Boolean_Spurious","reach":{"status":"ok"}}],"summary":{"ran":3,"unverified":4},"by_repo_kind":{"official":{"samples":7,"ran":3,"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":7,"samples":[{"code_sha256_prefix":"9ee9f6e04049c660","entry":"generate_random_func","repo":"NayutaQiu/Boolean_Spurious","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/NayutaQiu/Boolean_Spurious/blob/HEAD/src/utils.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":"9ee9f6e04049c660"}},{"code_sha256_prefix":"e7c9bd48e7074094","entry":"sample","repo":"NayutaQiu/Boolean_Spurious","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/NayutaQiu/Boolean_Spurious/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e7c9bd48e7074094"}},{"code_sha256_prefix":"8f49764ef07789fe","entry":"sample_index","repo":"NayutaQiu/Boolean_Spurious","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/NayutaQiu/Boolean_Spurious/blob/HEAD/src/utils.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":"8f49764ef07789fe"}},{"code_sha256_prefix":"e2f8b1a98dec9723","entry":"crop_and_resize","repo":"NayutaQiu/Boolean_Spurious","repo_kind":"official","path":"src/dataset_utils.py","file_url":"https://github.com/NayutaQiu/Boolean_Spurious/blob/HEAD/src/dataset_utils.py","link_basis":"plan_row","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":"e2f8b1a98dec9723"}},{"code_sha256_prefix":"fe461cfd1c998be0","entry":"get_enough_pos_neg_samples","repo":"NayutaQiu/Boolean_Spurious","repo_kind":"official","path":"src/dataset.py","file_url":"https://github.com/NayutaQiu/Boolean_Spurious/blob/HEAD/src/dataset.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":"fe461cfd1c998be0"}},{"code_sha256_prefix":"ce85e5419cc40a7a","entry":"original_combine_and_mask","repo":"NayutaQiu/Boolean_Spurious","repo_kind":"official","path":"src/dataset_utils.py","file_url":"https://github.com/NayutaQiu/Boolean_Spurious/blob/HEAD/src/dataset_utils.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":"ce85e5419cc40a7a"}},{"code_sha256_prefix":"2e1c243f6f6be9aa","entry":"original_crop_and_resize","repo":"NayutaQiu/Boolean_Spurious","repo_kind":"official","path":"src/dataset_utils.py","file_url":"https://github.com/NayutaQiu/Boolean_Spurious/blob/HEAD/src/dataset_utils.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":"2e1c243f6f6be9aa"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}