{"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-not-to-learn-training-deep-neural","title":"Learning Not to Learn: Training Deep Neural Networks with Biased Data","arxiv_id":"1812.10352","date":"2018-12-26","proceeding":"CVPR 2019 6","authors":["Byungju Kim","Hyunwoo Kim","Kyung-Su Kim","Sungjin Kim","Junmo Kim"],"abstract":"We propose a novel regularization algorithm to train deep neural networks, in\nwhich data at training time is severely biased. Since a neural network\nefficiently learns data distribution, a network is likely to learn the bias\ninformation to categorize input data. It leads to poor performance at test\ntime, if the bias is, in fact, irrelevant to the categorization. In this paper,\nwe formulate a regularization loss based on mutual information between feature\nembedding and bias. Based on the idea of minimizing this mutual information, we\npropose an iterative algorithm to unlearn the bias information. We employ an\nadditional network to predict the bias distribution and train the network\nadversarially against the feature embedding network. At the end of learning,\nthe bias prediction network is not able to predict the bias not because it is\npoorly trained, but because the feature embedding network successfully unlearns\nthe bias information. We also demonstrate quantitative and qualitative\nexperimental results which show that our algorithm effectively removes the bias\ninformation from feature embedding.","url_abs":"http://arxiv.org/abs/1812.10352v2","url_pdf":"http://arxiv.org/pdf/1812.10352v2.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-not-to-learn-training-deep-neural","repo_url":"https://github.com/2229761k/FAI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-not-to-learn-training-deep-neural","repo_url":"https://github.com/feidfoe/learning-not-to-learn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-not-to-learn-training-deep-neural","repo_url":"https://github.com/jiazhi412/strong_attribute_bias","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-not-to-learn-training-deep-neural","repo_url":"https://github.com/ys-zong/medfair","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.10352","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.10352"}},"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/ys-zong/medfair","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/feidfoe/learning-not-to-learn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jiazhi412/strong_attribute_bias","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2229761k/FAI","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"ran_honours":1},"by_repo_kind":{"listed":{"samples":1,"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":2,"samples":[{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"8a26ee1d7d102851","entry":"grad_reverse","repo":"feidfoe/learning-not-to-learn","repo_kind":"listed","path":"trainer.py","file_url":"https://github.com/feidfoe/learning-not-to-learn/blob/HEAD/trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8a26ee1d7d102851"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}