{"id":"W4382317875","doi":"10.1609/aaai.v37i12.26748","title":"Revisiting the Importance of Amplifying Bias for Debiasing","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Ministry of Science and ICT, South Korea; Korea Advanced Institute of Science and Technology; Institute for Information and Communications Technology Promotion; Electronics and Telecommunications Research Institute","keywords":"Debiasing; Selection bias; Computer science; Artificial intelligence; Classifier (UML); Sampling bias; Non-response bias; Training set; Sample (material); Statistics; Machine learning; Sample size determination; Psychology; Mathematics; Social psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005136572,0.001703432,0.001384779,0.001041295,0.0006999646,0.001346023,0.002361767,0.001563305,0.00187077],"category_scores_gemma":[0.02084095,0.0006136464,0.000966246,0.0008013513,0.001897899,0.003348981,0.002301337,0.002786212,0.0009392721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007479286,"about_ca_system_score_gemma":0.001207681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003297943,"about_ca_topic_score_gemma":0.005217594,"domain_scores_codex":[0.9977525,0.0005377711,0.0002336108,0.0006342853,0.0006515075,0.000190268],"domain_scores_gemma":[0.9906288,0.004427328,0.0007549581,0.002110037,0.001871896,0.0002069718],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009815111,0.0004373245,0.01467531,0.0006970218,0.0002610041,0.0002834497,0.0007882058,0.1334723,0.09910589,0.01098754,0.005102788,0.7332076],"study_design_scores_gemma":[0.00009847152,0.0005888969,0.005027938,0.000161713,0.0001547733,0.0003958322,0.000165645,0.9013106,0.07146418,0.0107673,0.00978982,0.0000748789],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1248219,0.003168026,0.8656421,0.000914019,0.0002681911,0.0002034644,0.0001581478,0.002570125,0.00225396],"genre_scores_gemma":[0.6021904,0.00103385,0.3895822,0.00104374,0.0002488783,0.0002394778,0.0006090305,0.0006693007,0.004383083],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005136572,"threshold_uncertainty_score":0.02716506,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1840778661745962,"score_gpt":0.3545708136863175,"score_spread":0.1704929475117214,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}