{"id":"W4404638964","doi":"10.1007/s11704-024-3575-5","title":"Soft-GNN: towards robust graph neural networks via self-adaptive data utilization","year":2024,"lang":"en","type":"article","venue":"Frontiers of Computer Science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Generality; Robustness (evolution); Graph; Data mining; Machine learning; Artificial intelligence; Noisy data; Training set; Artificial neural network; Pattern recognition (psychology); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001529892,0.001423021,0.001327514,0.001267471,0.0005079817,0.001100685,0.003321247,0.002286386,0.002696321],"category_scores_gemma":[0.008528817,0.0007415215,0.0007666934,0.001250424,0.00120274,0.002542929,0.003566354,0.002416488,0.001380377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009990085,"about_ca_system_score_gemma":0.001208988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006952728,"about_ca_topic_score_gemma":0.009925128,"domain_scores_codex":[0.9991511,0.0002536979,0.00004481227,0.0002466412,0.0002211365,0.00008253681],"domain_scores_gemma":[0.9973826,0.001229234,0.000186988,0.0005128048,0.0005767413,0.0001116087],"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":[0.0002246215,0.000120002,0.0006964116,0.0001364874,0.0001004137,0.00009876266,0.00007626032,0.7241623,0.005019532,0.01205845,0.005461419,0.2518454],"study_design_scores_gemma":[0.000003636941,0.00001001023,0.00002757284,0.000003806388,0.000004050898,0.000008034812,0.000004038947,0.9956557,0.0005494448,0.003522969,0.0002081324,0.000002652699],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01132055,0.0002789272,0.9845275,0.0002273992,0.00009132435,0.00005698262,0.0001061179,0.002430822,0.0009604664],"genre_scores_gemma":[0.4174636,0.0003218913,0.5740217,0.0006961056,0.0001273118,0.0002270703,0.0008000757,0.0009448671,0.005397373],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006952728,"threshold_uncertainty_score":0.01382452,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04234906727040412,"score_gpt":0.2712512761662814,"score_spread":0.2289022088958773,"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."}}