{"id":"W3200211247","doi":"10.14778/3485450.3485462","title":"Accelerating recommendation system training by leveraging popular choices","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Embedding; Recommender system; Categorical variable; Popularity; Parallel computing; Feature (linguistics); Representation (politics); Machine learning; Artificial intelligence","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":[0.0006723413,0.0006856609,0.0007941596,0.0006255237,0.0004818536,0.001079952,0.001818602,0.0009235611,0.004566601],"category_scores_gemma":[0.006131972,0.0007737358,0.0006769887,0.001251006,0.0004171256,0.002546416,0.001267146,0.001373949,0.00324455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005322853,"about_ca_system_score_gemma":0.0009258174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009717929,"about_ca_topic_score_gemma":0.02246052,"domain_scores_codex":[0.9991921,0.0001573817,0.00005710439,0.0002610768,0.0002294074,0.0001029995],"domain_scores_gemma":[0.997741,0.0009044828,0.00009902671,0.0007714721,0.0003967658,0.00008724104],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009480838,0.0005984327,0.02010429,0.0002649529,0.0001899931,0.0002782689,0.0005826643,0.192404,0.03123929,0.004158298,0.0137344,0.7354973],"study_design_scores_gemma":[0.00005065117,0.0001387875,0.001902648,0.00001275081,0.00002734005,0.00009516026,0.00009530357,0.9803877,0.009598402,0.004281101,0.003390833,0.0000193231],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2195842,0.001326839,0.7565171,0.0006637826,0.0001807696,0.0001719208,0.001265735,0.01496404,0.005325767],"genre_scores_gemma":[0.6155521,0.0004274166,0.3757674,0.0001801008,0.00006803469,0.0001954296,0.002683339,0.0003764409,0.004749675],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009717929,"threshold_uncertainty_score":0.01932275,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04706617408481114,"score_gpt":0.2487423492667841,"score_spread":0.2016761751819729,"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."}}