{"id":"W4414166064","doi":"10.1109/tmm.2025.3607712","title":"Oversampling With GAN via Meta-Learning for Imbalanced Data","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Oversampling; Discriminator; Generator (circuit theory); Consistency (knowledge bases); Mode (computer interface); Pattern recognition (psychology); Contrast (vision); Bayesian probability","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000335144,0.000207922,0.0002834771,0.0002472357,0.0002924975,0.0001252009,0.001407897,0.00008891647,0.0000212264],"category_scores_gemma":[0.00003397862,0.0001762579,0.00008636015,0.0005478192,0.00006681449,0.0007502986,0.00000866016,0.0003117198,0.00002019518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006662571,"about_ca_system_score_gemma":0.0001072147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003003101,"about_ca_topic_score_gemma":0.00003136908,"domain_scores_codex":[0.9984375,0.00005782651,0.0002642711,0.0007200157,0.0002277678,0.0002926342],"domain_scores_gemma":[0.9975522,0.0005427033,0.0001099034,0.001595733,0.00012855,0.0000709153],"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":[0.0003410921,0.0008071476,0.0001116871,0.0001830534,0.002563115,0.000009079457,0.0008360415,0.03862294,0.05240256,0.00221508,0.004752303,0.8971559],"study_design_scores_gemma":[0.0008509209,0.0001188717,0.0001436883,0.0000377451,0.0003021145,0.000003788718,0.00002626964,0.8511928,0.1331034,0.0003003078,0.01364141,0.0002786654],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00004486327,0.00003085523,0.9971856,0.0007742013,0.0003503749,0.0005320623,0.0001002165,0.0007553443,0.0002265084],"genre_scores_gemma":[0.4181153,0.00002896508,0.5805295,0.0003074213,0.00002136214,0.0003154005,0.0000711605,0.00001798389,0.0005930087],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8968772,"threshold_uncertainty_score":0.7187588,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06123201054746646,"score_gpt":0.3169810771726663,"score_spread":0.2557490666251998,"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."}}