{"id":"W4287198239","doi":"10.48550/arxiv.2104.13014","title":"Node Embedding using Mutual Information and Self-Supervision based\\n Bi-level Aggregation","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Aggregate (composite); Leverage (statistics); Exploit; Node (physics); Embedding; Theoretical computer science; Cluster analysis; Graph; Range (aeronautics); Data mining; Artificial intelligence; Computer security","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000959357,0.001031865,0.001323046,0.001369067,0.0004727769,0.0009424638,0.002264806,0.001312635,0.001259334],"category_scores_gemma":[0.004253351,0.0007071698,0.0010703,0.001417458,0.001055361,0.003043302,0.001588334,0.00187691,0.0005174478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001170227,"about_ca_system_score_gemma":0.0007804998,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009122387,"about_ca_topic_score_gemma":0.01284915,"domain_scores_codex":[0.9991378,0.0002060199,0.00005111248,0.0003309647,0.0001933927,0.00008073565],"domain_scores_gemma":[0.9981732,0.0007081766,0.0003407482,0.0003404062,0.0003396885,0.00009768569],"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":[0.0002122962,0.000169816,0.005933222,0.0001394135,0.0001732887,0.0001754284,0.0002620783,0.8210437,0.003158091,0.01394495,0.00504031,0.1497474],"study_design_scores_gemma":[0.000002713811,0.000009472972,0.0001896612,0.000003857795,0.000006588273,0.000009511898,0.000003770601,0.9966843,0.0002413659,0.002680018,0.000165267,0.000003528669],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09536251,0.0008779864,0.8979725,0.0006030584,0.00009868252,0.00007488864,0.0003979599,0.002168927,0.002443479],"genre_scores_gemma":[0.9006282,0.0003429365,0.09340602,0.0002298225,0.0001280456,0.0001187365,0.001063657,0.0001728896,0.003909636],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009122387,"threshold_uncertainty_score":0.01813853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06614258378080558,"score_gpt":0.2064764152930668,"score_spread":0.1403338315122612,"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."}}