{"id":"W2808483757","doi":"10.24963/ijcai.2018/475","title":"Lightweight Label Propagation for Large-Scale Network Data","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Novelis (Canada)","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Computer science; Process (computing); Overhead (engineering); Scale (ratio); Graph; Theoretical computer science; Stochastic gradient descent; Algorithm; Data mining; Artificial intelligence; Artificial neural network","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":[0.0003041072,0.0001206501,0.0001191138,0.00003092279,0.0002748171,0.0000991846,0.001630991,0.00005896839,0.00001815851],"category_scores_gemma":[0.00002421466,0.0000950209,0.00002418631,0.0004984131,0.00003781037,0.001097552,0.0007478041,0.00007465225,0.00007110346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001083055,"about_ca_system_score_gemma":0.00002270906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001232272,"about_ca_topic_score_gemma":0.000102342,"domain_scores_codex":[0.9985794,0.00002702139,0.000188996,0.0005872059,0.0001619065,0.0004555116],"domain_scores_gemma":[0.9981887,0.00009383456,0.00007851898,0.001423602,0.0001342572,0.00008105123],"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":[0.00003091929,0.000125943,0.0005616896,0.00001483483,0.00002280895,0.000002717188,0.0001840449,0.0001422161,0.000367031,0.601941,0.3371835,0.05942326],"study_design_scores_gemma":[0.0003815585,0.0001418808,0.0001493692,0.00001179042,0.000004638478,0.000003731806,0.000003020384,0.7984014,0.001064588,0.03277745,0.1668946,0.0001660077],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003089085,0.00008028137,0.9937125,0.001538405,0.0008544039,0.0003972061,0.000009144191,0.000325857,0.002773329],"genre_scores_gemma":[0.04286611,0.00001370251,0.9510139,0.001981706,0.001745509,0.00003817275,0.00006753931,0.00001856903,0.002254809],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7982591,"threshold_uncertainty_score":0.387484,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03688565519832589,"score_gpt":0.2957454536896494,"score_spread":0.2588597984913236,"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."}}