{"id":"W4379522898","doi":"10.21428/594757db.0041f830","title":"Meta-GCN: A Dynamically Weighted Loss Minimization Method for Dealing with the Data Imbalance in Graph Neural Networks","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Outlier; Computer science; Skewness; Graph; Artificial neural network; Minification; Artificial intelligence; Set (abstract data type); Data set; Pattern recognition (psychology); Machine learning; Data mining; Algorithm; Mathematics; Statistics; Theoretical computer science","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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004269852,0.0004917943,0.00105719,0.0001835134,0.0007997175,0.00004882184,0.001841965,0.0008851922,0.0001741983],"category_scores_gemma":[0.0005544029,0.0002966455,0.0001827356,0.0005486849,0.0001247425,0.0001386477,0.001870502,0.002879599,0.00001925949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000178613,"about_ca_system_score_gemma":0.0004995586,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.0153216,"about_ca_topic_score_gemma":0.1656642,"domain_scores_codex":[0.9936101,0.001978477,0.001598817,0.00136618,0.0004198134,0.00102661],"domain_scores_gemma":[0.9885839,0.007363657,0.0008895128,0.002349655,0.0006544755,0.0001588214],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001561017,0.0001387915,0.07126117,0.003375424,0.002464839,0.00006350911,0.00621312,0.8623734,0.000006107584,0.03114862,0.01009748,0.01129659],"study_design_scores_gemma":[0.0001444909,0.00004138693,0.001150162,0.00031584,0.0005591051,0.000001243327,0.001339475,0.9860079,0.000002420978,0.009500152,0.0006152375,0.0003225901],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003276767,0.0006269471,0.9555475,0.03119019,0.001624488,0.006636382,0.0005492292,0.0003966815,0.0001517867],"genre_scores_gemma":[0.4797836,0.001723288,0.4806439,0.01020283,0.002374968,0.01216273,0.009277769,0.0006570689,0.003173887],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4765068,"threshold_uncertainty_score":0.9999486,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3960692074295682,"score_gpt":0.520168301933918,"score_spread":0.1240990945043498,"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."}}