{"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/signal-is-harder-to-learn-than-bias-debiasing","title":"Signal Is Harder To Learn Than Bias: Debiasing with Focal Loss","arxiv_id":"2305.19671","date":"2023-05-31","proceeding":null,"authors":["Moritz Vandenhirtz","Laura Manduchi","Ričards Marcinkevičs","Julia E. Vogt"],"abstract":"Spurious correlations are everywhere. While humans often do not perceive them, neural networks are notorious for learning unwanted associations, also known as biases, instead of the underlying decision rule. As a result, practitioners are often unaware of the biased decision-making of their classifiers. Such a biased model based on spurious correlations might not generalize to unobserved data, leading to unintended, adverse consequences. We propose Signal is Harder (SiH), a variational-autoencoder-based method that simultaneously trains a biased and unbiased classifier using a novel, disentangling reweighting scheme inspired by the focal loss. Using the unbiased classifier, SiH matches or improves upon the performance of state-of-the-art debiasing methods. To improve the interpretability of our technique, we propose a perturbation scheme in the latent space for visualizing the bias that helps practitioners become aware of the sources of spurious correlations.","url_abs":"https://arxiv.org/abs/2305.19671v1","url_pdf":"https://arxiv.org/pdf/2305.19671v1.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":"signal-is-harder-to-learn-than-bias-debiasing","repo_url":"https://github.com/mvandenhi/signal-is-harder","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"unfairness-detection","task_name":"Unfairness Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.19671","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.19671"}},"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/mvandenhi/signal-is-harder","reach":null}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":4,"samples":[{"code_sha256_prefix":"3e7d8d2b6082064a","entry":"MLP_Classifier","repo":"mvandenhi/signal-is-harder","repo_kind":"official","path":"module/mlp_vae.py","file_url":"https://github.com/mvandenhi/signal-is-harder/blob/HEAD/module/mlp_vae.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":"3e7d8d2b6082064a"}},{"code_sha256_prefix":"3854115ba0fbf0d0","entry":"MLP_Decoder","repo":"mvandenhi/signal-is-harder","repo_kind":"official","path":"module/mlp_vae.py","file_url":"https://github.com/mvandenhi/signal-is-harder/blob/HEAD/module/mlp_vae.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":"3854115ba0fbf0d0"}},{"code_sha256_prefix":"db0278126eaa0bfc","entry":"MLP_Encoder","repo":"mvandenhi/signal-is-harder","repo_kind":"official","path":"module/mlp_vae.py","file_url":"https://github.com/mvandenhi/signal-is-harder/blob/HEAD/module/mlp_vae.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":"db0278126eaa0bfc"}},{"code_sha256_prefix":"15c25c22f1d6927c","entry":"MLP_VAE","repo":"mvandenhi/signal-is-harder","repo_kind":"official","path":"module/mlp_vae.py","file_url":"https://github.com/mvandenhi/signal-is-harder/blob/HEAD/module/mlp_vae.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":"15c25c22f1d6927c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}