{"id":"W4287982101","doi":"10.1093/bib/bbac279","title":"Implications of Topological Imbalance for Representation Learning on Biomedical Knowledge Graphs","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Canadian Institute for Advanced Research; HEC Montréal","funders":"","keywords":"Computer science; Inference; Embedding; Machine learning; Representation (politics); Theoretical computer science; Graph; Knowledge graph; Artificial intelligence; Data science; Data mining","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":[0.007920998,0.0006787614,0.0009059366,0.003421226,0.001579652,0.003105477,0.001075966,0.001383278,0.00284938],"category_scores_gemma":[0.08304417,0.0004299228,0.0007435898,0.002927575,0.00216292,0.006319962,0.002568364,0.002648118,0.0004170489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001855638,"about_ca_system_score_gemma":0.0007420849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001869406,"about_ca_topic_score_gemma":0.002194405,"domain_scores_codex":[0.9955897,0.002079373,0.0002983411,0.0008652385,0.0009359042,0.0002313334],"domain_scores_gemma":[0.9223144,0.0644101,0.004077733,0.005577504,0.002670985,0.0009492948],"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":[0.001179389,0.0004368014,0.07408629,0.000686978,0.0003402113,0.0007533293,0.001716961,0.4938931,0.006707149,0.223032,0.01082463,0.1863431],"study_design_scores_gemma":[0.00004430659,0.00009651734,0.004920711,0.00006875905,0.00005374018,0.0003038002,0.0003053045,0.5690176,0.002664754,0.4198654,0.002629284,0.00002980857],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5464382,0.001574281,0.4283976,0.01055203,0.0002137974,0.0001594942,0.002925168,0.001197126,0.008542417],"genre_scores_gemma":[0.9534578,0.0005541639,0.04165507,0.0004812079,0.0001548991,0.0001020224,0.002642321,0.000125658,0.0008268002],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007920998,"threshold_uncertainty_score":0.04189074,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04786946096316707,"score_gpt":0.2291345781142058,"score_spread":0.1812651171510387,"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."}}