{"id":"W4386691567","doi":"10.52953/afyw5455","title":"Designing graph neural networks training data with limited samples and small network sizes","year":2023,"lang":"en","type":"article","venue":"ITU Journal on Future and Evolving Technologies","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Mitacs","keywords":"Computer science; Artificial neural network; Pipeline (software); Graph; Artificial intelligence; Data mining; Machine learning; Training set; Baseline (sea); Domain (mathematical analysis); Feature (linguistics); Small data; Node (physics); Engineering; Theoretical computer science; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005884314,0.0003404975,0.0003785103,0.0003720662,0.0009114759,0.0006693167,0.001540681,0.0002284964,6.621594e-7],"category_scores_gemma":[0.0001887648,0.0002400113,0.00004428234,0.001649467,0.0002400973,0.0009635626,0.001042446,0.00120367,5.769783e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001345281,"about_ca_system_score_gemma":0.00002146124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001595064,"about_ca_topic_score_gemma":0.00002498323,"domain_scores_codex":[0.9979048,0.00008224055,0.0003068187,0.0006659782,0.0002452806,0.0007948713],"domain_scores_gemma":[0.9980567,0.0006978244,0.0002507602,0.0008119643,0.00007134007,0.0001113987],"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":[0.0001113346,0.00002058706,0.01018121,0.00002531021,0.0001733524,0.0008674592,0.0006102745,0.1072405,0.0001686447,0.007763606,0.01070933,0.8621284],"study_design_scores_gemma":[0.00130797,0.001419884,0.01714043,0.0008924448,0.00008663492,0.002527247,0.004676727,0.9010422,0.00008749667,0.0646015,0.004944466,0.001272966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1092587,0.02365448,0.8451337,0.01475023,0.001524201,0.0003615241,0.000005646836,0.005252613,0.00005886767],"genre_scores_gemma":[0.7825712,0.007016237,0.2093526,0.0003805032,0.0006179645,0.000008201286,0.000008363096,0.00003450086,0.00001039736],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8608555,"threshold_uncertainty_score":0.9787379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05848140215441747,"score_gpt":0.250777585829844,"score_spread":0.1922961836754265,"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."}}