{"id":"W4392368241","doi":"10.1145/3616855.3635859","title":"MultiFS: Automated Multi-Scenario Feature Selection in Deep Recommender Systems","year":2024,"lang":"en","type":"article","venue":"","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Hong Kong Institute for Data Science; National Natural Science Foundation of China; Innovation and Technology Fund; Universitas Brawijaya; Impact Fund; City University of Hong Kong; Aromatic Plant Research Center","keywords":"Computer science; Recommender system; Feature (linguistics); Bridge (graph theory); Feature selection; Artificial intelligence; Machine learning; Selection (genetic algorithm); 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005211088,0.0002093076,0.0002347929,0.0003789809,0.00007364414,0.0007535463,0.0004589152,0.0002085332,0.00001233804],"category_scores_gemma":[0.00001226548,0.0001656181,0.00007167501,0.0009154695,0.000009207793,0.0007137034,0.0001291564,0.0003333089,0.00007590842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000255564,"about_ca_system_score_gemma":0.0000570332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001411103,"about_ca_topic_score_gemma":0.0008788407,"domain_scores_codex":[0.998421,0.0001550307,0.000332157,0.0005622849,0.0001824094,0.0003471196],"domain_scores_gemma":[0.9994542,0.00007833733,0.000047185,0.0002857971,0.00005712746,0.00007736682],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001479624,0.0007868563,0.009571861,0.00135552,0.0003503761,0.0003418193,0.009120593,0.001787131,0.006717472,0.1260508,0.6375809,0.2063219],"study_design_scores_gemma":[0.000179692,0.00003782188,0.001177183,0.0001690755,0.000002472068,0.00008862193,0.00007471746,0.9508241,0.000552216,0.00007440218,0.04660254,0.0002171436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00068396,0.001239945,0.9820385,0.001853098,0.001768665,0.0005636836,0.000001191857,0.008290078,0.003560856],"genre_scores_gemma":[0.8800728,0.00004953532,0.1157209,0.0002090327,0.0001019514,0.0001505102,0.00000497179,0.00002971085,0.003660636],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.949037,"threshold_uncertainty_score":0.7266464,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02368038919726357,"score_gpt":0.2903076922954795,"score_spread":0.266627303098216,"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."}}