{"id":"W4403518872","doi":"10.3233/faia240779","title":"Every Node Counts: Improving the Training of Graph Neural Networks on Node Classification","year":2024,"lang":"en","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Node (physics); Computer science; Training (meteorology); Artificial neural network; Graph; Artificial intelligence; Computer network; Theoretical computer science; Engineering; Geography","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":[0.000224445,0.000140259,0.0001581192,0.0001595312,0.0001198122,0.00009064351,0.0004182995,0.0001236304,0.000008643833],"category_scores_gemma":[0.000009933483,0.0001149491,0.00006312235,0.0001511338,0.0001401611,0.00005386348,0.00006145986,0.0003920993,0.0000289229],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002462424,"about_ca_system_score_gemma":0.00002940631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001429416,"about_ca_topic_score_gemma":0.00000609993,"domain_scores_codex":[0.9990602,0.00001340202,0.0003080225,0.0003430397,0.0001371301,0.0001382411],"domain_scores_gemma":[0.999341,0.00007629629,0.0001334424,0.0003842734,0.00003393088,0.00003104397],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001939853,0.000006713427,0.000005706591,0.00001128274,0.000007326431,4.040971e-7,0.000173197,0.003123223,0.000003515553,0.5105069,0.0005923065,0.4855675],"study_design_scores_gemma":[0.00000648141,0.00001679234,0.00001572361,0.0000669244,0.00001667399,0.000001562157,0.0001272189,0.750955,0.00001369249,0.2162819,0.03236141,0.0001366471],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000008831348,0.001021956,0.9378938,0.0007524913,0.0005156641,0.0002214567,0.000007441464,0.00005597081,0.05952238],"genre_scores_gemma":[0.8764444,0.00272901,0.02715157,0.001809526,0.002205758,0.0005808975,0.0001331885,0.0001702309,0.08877545],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9107422,"threshold_uncertainty_score":0.4687488,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0453633208687108,"score_gpt":0.2706630042142926,"score_spread":0.2252996833455818,"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."}}