{"id":"W4200630255","doi":"10.1093/bib/bbac279","title":"Implications of topological imbalance for representation learning on biomedical knowledge graphs","year":2022,"lang":"en","type":"preprint","venue":"Briefings in Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Canadian Institute for Advanced Research; HEC Montréal","funders":"","keywords":"Inference; Computer science; Embedding; Theoretical computer science; Domain knowledge; Graph embedding; Representation (politics); Graph; Knowledge graph; Topological graph theory; Machine learning; Biological network; Artificial intelligence; 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":[0.007773395,0.0007702326,0.001003,0.003280974,0.001563002,0.003461081,0.001212046,0.001700918,0.003849834],"category_scores_gemma":[0.08367417,0.0005048595,0.0008956212,0.003104718,0.002630545,0.007241212,0.003051253,0.003348811,0.0005200824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001863168,"about_ca_system_score_gemma":0.0006824388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00149519,"about_ca_topic_score_gemma":0.0015221,"domain_scores_codex":[0.9946478,0.002502309,0.0003441442,0.001054632,0.001187002,0.00026417],"domain_scores_gemma":[0.9225294,0.0633731,0.004078723,0.006070178,0.002834081,0.00111454],"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":[0.001077819,0.0003514742,0.0460938,0.0008288532,0.0003136826,0.0008457141,0.001799084,0.4020245,0.007087702,0.3276306,0.01552766,0.1964191],"study_design_scores_gemma":[0.00004296704,0.00008653967,0.003145817,0.0000797742,0.000046048,0.0003306404,0.0002598268,0.419943,0.00280071,0.5695468,0.003686353,0.0000315383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3845272,0.002330995,0.5840034,0.0147362,0.0003824084,0.0001588714,0.003147207,0.001355586,0.009358237],"genre_scores_gemma":[0.9267156,0.001140468,0.06562751,0.0008061922,0.0003420135,0.0001473762,0.003464357,0.0002315696,0.001524945],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007773395,"threshold_uncertainty_score":0.04111016,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02507420569848868,"score_gpt":0.3141767155849239,"score_spread":0.2891025098864353,"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."}}