{"id":"W3088352442","doi":"10.18653/v1/2020.emnlp-main.492","title":"Structure Aware Negative Sampling in Knowledge Graphs","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Institut de Valorisation des Données; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Adversarial system; Computer science; Embedding; Discriminative model; Scalability; Graph; Sampling (signal processing); Theoretical computer science; Simple (philosophy); Artificial intelligence; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0000672338,0.0004437029,0.0004961084,0.0002663398,0.00007247145,0.0001804069,0.002136738,0.0003491985,0.00002364333],"category_scores_gemma":[0.0000599849,0.0004051547,0.0001728781,0.001108197,0.00006419606,0.0002823171,0.003743078,0.001835683,0.00001562595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007991809,"about_ca_system_score_gemma":0.000135365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003877877,"about_ca_topic_score_gemma":0.00041285,"domain_scores_codex":[0.9975309,0.0001129385,0.0004073254,0.001283933,0.0002264954,0.0004383644],"domain_scores_gemma":[0.9983586,0.0002618178,0.0001854326,0.0009218581,0.0001044816,0.0001677852],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004133212,0.0001241194,0.003220023,0.0005379411,0.0001580906,0.0002289906,0.008723598,0.1822876,0.0006276882,0.6898345,0.003857462,0.1103587],"study_design_scores_gemma":[0.0002343655,0.00002778667,0.002885726,0.0001779921,0.000005002645,0.000005002375,0.00003743986,0.1875888,0.0006425622,0.8075358,0.0003045579,0.0005549502],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008045047,0.0008506468,0.9847656,0.001295411,0.001932679,0.0006877378,0.00002791743,0.0006878534,0.001707112],"genre_scores_gemma":[0.8178236,0.00008431223,0.1812864,0.0005331971,0.000141493,0.00002717702,0.00002035679,0.00002839738,0.00005501437],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8097786,"threshold_uncertainty_score":0.99984,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04925334177672447,"score_gpt":0.3141465519389159,"score_spread":0.2648932101621915,"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."}}