{"id":"W3092206109","doi":"10.1609/aaai.v35i11.17203","title":"GraphMix: Improved Training of GNNs for Semi-Supervised Learning","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":113,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Graph; Convolutional neural network; Theoretical computer science; Artificial intelligence; Machine learning; Regularization (linguistics); 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":[0.0004273824,0.0002451866,0.000412499,0.0001226395,0.0002243913,0.0001271181,0.001587176,0.0001102488,0.00001999958],"category_scores_gemma":[0.0008843141,0.0002030836,0.0002768224,0.001122928,0.0002497361,0.0003571576,0.0003607503,0.0003930716,0.000003326778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002112245,"about_ca_system_score_gemma":0.0001424169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006782543,"about_ca_topic_score_gemma":0.000007896771,"domain_scores_codex":[0.9978869,0.00002501325,0.0006710651,0.000601068,0.0003605714,0.0004553932],"domain_scores_gemma":[0.9975364,0.0002946698,0.0005201087,0.0003221782,0.001229952,0.00009674401],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005126948,0.00005989534,0.0001189382,0.00006257864,0.00002136346,4.412337e-7,0.001789458,0.0005152652,0.3524923,0.5363854,0.00002248447,0.1084806],"study_design_scores_gemma":[0.00004864394,0.0002101657,0.00004593157,0.000196474,0.00001280261,0.000004765016,0.001052029,0.2203877,0.6262359,0.1515493,0.00007330107,0.0001829988],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3177175,0.000171639,0.66965,0.004306404,0.001186839,0.001181897,0.00001470474,0.0002772779,0.005493795],"genre_scores_gemma":[0.976676,0.0000564165,0.02280969,0.0001561426,0.00006044444,0.0000404213,0.000001044797,0.00001857262,0.0001812941],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6589585,"threshold_uncertainty_score":0.8281507,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0913165739348398,"score_gpt":0.2977802692848069,"score_spread":0.2064636953499671,"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."}}