{"id":"W3125117642","doi":"","title":"On Batch-size Selection for Stochastic Training for Graph Neural Networks","year":2021,"lang":"en","type":"article","venue":"","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Complement (music); Metric (unit); Artificial neural network; Randomness; Selection (genetic algorithm); Stochastic gradient descent; Graph; Batch processing; Contrast (vision); Artificial intelligence; Estimator; Machine learning; Mathematics; Statistics; Theoretical computer science; Engineering","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":[0.0001421984,0.0001933752,0.0002135413,0.00006121599,0.0002766883,0.0001256767,0.0003345648,0.00008994558,0.000009267993],"category_scores_gemma":[0.0002210805,0.0001826422,0.0002009322,0.0006954226,0.00002541869,0.000329463,0.00006049879,0.0001770223,9.46092e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002624707,"about_ca_system_score_gemma":0.00003451051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001467097,"about_ca_topic_score_gemma":0.00003744649,"domain_scores_codex":[0.9984328,0.00003637556,0.0002314396,0.0006034165,0.0001469754,0.0005490259],"domain_scores_gemma":[0.9975555,0.001788556,0.00008153789,0.000296852,0.0001659672,0.0001116156],"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":[0.00006119625,0.00003450304,0.000008725056,0.000008047712,0.00002137871,0.000002190902,0.00009894963,0.8037306,0.0002521311,0.1253765,0.002226983,0.0681788],"study_design_scores_gemma":[0.0006567001,0.0003176449,0.00006772432,0.00001385884,0.000009308103,0.00002470227,0.00002166675,0.9330687,0.000253965,0.06516846,0.0001866603,0.0002106047],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002692524,0.00006240702,0.9943201,0.0008582345,0.001127926,0.0005013162,0.000002257557,0.0003142963,0.0001209564],"genre_scores_gemma":[0.8346206,0.000002673461,0.1622015,0.002129816,0.0003036117,0.0002130518,0.000008297926,0.00002622013,0.000494222],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8321186,"threshold_uncertainty_score":0.7447935,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02856819917791627,"score_gpt":0.272625345351232,"score_spread":0.2440571461733157,"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."}}