{"id":"W2971325383","doi":"10.48550/arxiv.1906.07159","title":"vGraph: A Generative Model for Joint Community Detection and Node\\n Representation Learning","year":2019,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; HEC Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Generative model; Node (physics); Representation (politics); Inference; Graph; Feature learning; Parameterized complexity; Generative grammar; Community structure; Theoretical computer science; Machine learning; Joint probability distribution; Artificial intelligence; Algorithm; Mathematics","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":[0.001916057,0.001249928,0.001248474,0.002598636,0.0009043399,0.001574726,0.004385463,0.002328302,0.003149854],"category_scores_gemma":[0.006432047,0.001117681,0.001885414,0.002361187,0.001726519,0.002818883,0.002458597,0.002683215,0.001339474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001832615,"about_ca_system_score_gemma":0.001465836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01125742,"about_ca_topic_score_gemma":0.02180869,"domain_scores_codex":[0.9989028,0.0004069407,0.00002786183,0.0003850975,0.00018921,0.00008808007],"domain_scores_gemma":[0.9979907,0.001180626,0.0001739491,0.0003549909,0.0001696441,0.0001301349],"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":[0.0001354756,0.0001337358,0.004099833,0.0001846015,0.000253065,0.0003192924,0.0003651174,0.6619186,0.003154766,0.1543872,0.02159581,0.1534525],"study_design_scores_gemma":[0.000009815129,0.000008175103,0.0001522222,0.00001249248,0.000009737624,0.00005327193,0.00001387765,0.9447609,0.0003649926,0.05241569,0.002190967,0.000007880739],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00486264,0.0002196688,0.9924328,0.0002425368,0.00003473521,0.00004733527,0.0003830113,0.0009777175,0.000799619],"genre_scores_gemma":[0.339018,0.0007810329,0.6437203,0.0008182766,0.0002155338,0.0004826785,0.005157516,0.001077953,0.008728663],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01125742,"threshold_uncertainty_score":0.02238375,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1358008619107201,"score_gpt":0.2308524273954221,"score_spread":0.09505156548470195,"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."}}