{"id":"W4393161100","doi":"10.1609/aaai.v38i19.30157","title":"Toward Robustness in Multi-Label Classification: A Data Augmentation Strategy against Imbalance and Noise","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Robustness (evolution); Computer science; Artificial intelligence; Machine learning; Noise (video); Pattern recognition (psychology); Biology","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":[0.009330565,0.002289138,0.002053762,0.002035434,0.001409772,0.002774107,0.004278686,0.002633609,0.001668382],"category_scores_gemma":[0.02311863,0.0009238754,0.001636899,0.001909035,0.002887212,0.005274687,0.006001203,0.00501309,0.001680333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009896763,"about_ca_system_score_gemma":0.00144028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001100475,"about_ca_topic_score_gemma":0.001553694,"domain_scores_codex":[0.9939411,0.002207694,0.0002574759,0.001894531,0.001384031,0.0003152243],"domain_scores_gemma":[0.9886767,0.00471972,0.00113187,0.003482108,0.001571062,0.0004184904],"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":[0.001282233,0.0008053581,0.01335256,0.0005401669,0.0003338726,0.0002821008,0.001389704,0.184275,0.04416119,0.01912088,0.01571461,0.7187423],"study_design_scores_gemma":[0.00009075995,0.0002266344,0.001339575,0.00006386874,0.00006343199,0.0001737005,0.0001926267,0.9409692,0.01733915,0.03360318,0.005889133,0.00004869315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03182076,0.0006265152,0.9622165,0.0008439919,0.0001914968,0.0001564186,0.000276362,0.002638663,0.001229382],"genre_scores_gemma":[0.4022776,0.0003418573,0.5891415,0.001491197,0.0005394109,0.0006141762,0.001806953,0.0007681299,0.003019065],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009330565,"threshold_uncertainty_score":0.04934537,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3069820286734306,"score_gpt":0.3734675280781951,"score_spread":0.0664854994047645,"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."}}