{"id":"W4223925960","doi":"10.1016/j.ins.2022.04.027","title":"Federated against the cold: A trust-based federated learning approach to counter the cold start problem in recommendation systems","year":2022,"lang":"en","type":"article","venue":"Information Sciences","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":121,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; Concordia University; Université du Québec en Outaouais","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Cold start (automotive); MovieLens; Recommender system; Machine learning; Artificial intelligence; Benchmark (surveying); Deep learning; Collaborative filtering; Credibility; Information retrieval","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":["sts","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.005194854,0.0001426012,0.000135683,0.0003466139,0.00258171,0.002854354,0.009452807,0.0000454433,0.00001024195],"category_scores_gemma":[0.002142327,0.00009131931,0.00002434707,0.003324308,0.0001498084,0.002771059,0.009035772,0.0004517694,0.00003040661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003057504,"about_ca_system_score_gemma":0.0003375637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002517812,"about_ca_topic_score_gemma":0.00002502257,"domain_scores_codex":[0.9975182,0.0004323441,0.0005511218,0.0002915142,0.000837727,0.0003690555],"domain_scores_gemma":[0.9982629,0.0002782718,0.0003492971,0.0009132555,0.0001597919,0.00003649234],"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":[0.00003765042,0.0001415944,0.002195576,0.00006274259,0.00002168983,0.000001563435,0.004771364,0.6962428,0.0006301015,0.01127353,0.2583983,0.02622306],"study_design_scores_gemma":[0.0002155073,0.00008669907,0.0001093256,0.00001445285,9.484597e-7,0.00000482785,0.003648732,0.9000716,0.0001787882,0.0001638419,0.09537766,0.0001276771],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0435835,0.00003751502,0.8460344,0.08638938,0.0008862519,0.003006322,0.0000546697,0.001016777,0.01899115],"genre_scores_gemma":[0.9824015,0.000003379116,0.01329278,0.003444232,0.00001014252,0.0007434635,0.00005691023,0.000004379246,0.00004321214],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.938818,"threshold_uncertainty_score":0.998979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04101153043900531,"score_gpt":0.266815788954355,"score_spread":0.2258042585153497,"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."}}