{"id":"W3070904253","doi":"10.48550/arxiv.2008.08838","title":"Training Matters: Unlocking Potentials of Deeper Graph Convolutional Neural Networks","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Graph; Training (meteorology); Perspective (graphical); Expressive power; Convolutional neural network; Artificial intelligence; Machine learning; Operator (biology); Limit (mathematics); Risk analysis (engineering); Theoretical computer science; Mathematics; Business","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":[0.001743713,0.001008125,0.0005346722,0.0004546292,0.0004096501,0.001210834,0.001393476,0.001277508,0.002691609],"category_scores_gemma":[0.01160239,0.0004769308,0.0004047988,0.0004334653,0.001833713,0.00574845,0.002589278,0.002798281,0.0006022258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006596416,"about_ca_system_score_gemma":0.0006469555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001677506,"about_ca_topic_score_gemma":0.003122448,"domain_scores_codex":[0.9994553,0.0002261178,0.00002124868,0.0001175048,0.000116477,0.00006337142],"domain_scores_gemma":[0.9967585,0.002072209,0.0002039184,0.0006476073,0.0001850052,0.000132821],"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":[0.0006308072,0.0001904707,0.003978309,0.0003916429,0.0000937596,0.0003100796,0.0006879308,0.4400317,0.03390168,0.1436332,0.00486437,0.371286],"study_design_scores_gemma":[0.00001798556,0.0001055139,0.0004300584,0.00004961978,0.00002065704,0.00006447903,0.00005302833,0.8421603,0.005503515,0.1488749,0.002707202,0.00001272118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1433304,0.001684084,0.8413845,0.003701488,0.0001386728,0.00004675062,0.000105226,0.00158173,0.008027068],"genre_scores_gemma":[0.8723007,0.001028736,0.1220892,0.0006849074,0.0001408658,0.00004773608,0.0001777125,0.0004751763,0.003055054],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002691609,"threshold_uncertainty_score":0.009221792,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1043788125263583,"score_gpt":0.2004482211609255,"score_spread":0.09606940863456725,"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."}}