{"id":"W4392370875","doi":"10.54254/2755-2721/44/20230093","title":"Applying self-attention model to learn both Empirical Risk Minimization and Invariant Risk Minimization for multimedia recommendation","year":2024,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Recommender system; Computer science; Invariant (physics); Minification; Preference; Empirical risk minimization; Machine learning; Artificial intelligence; Empirical research; World Wide Web; Mathematics; Statistics","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":[0.0003183602,0.0001539378,0.0001445353,0.0002194371,0.0001544637,0.0003088815,0.00009038977,0.00007925992,9.313256e-7],"category_scores_gemma":[0.00002451051,0.0001570596,0.00003103687,0.0002404808,0.00000545563,0.0002880498,0.00008042624,0.0001191656,0.000002152049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004682011,"about_ca_system_score_gemma":0.00003034748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009563759,"about_ca_topic_score_gemma":0.00000117979,"domain_scores_codex":[0.9989991,0.00002205972,0.0002761623,0.0004178859,0.000128877,0.000155922],"domain_scores_gemma":[0.9994364,0.0002734083,0.00006945374,0.00008643798,0.00004598595,0.00008828477],"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":[0.000008325894,0.00003227425,0.0002312066,0.0001503883,0.00006325722,5.41185e-7,0.001451651,0.735272,0.0002330726,0.03309698,0.0008721765,0.2285881],"study_design_scores_gemma":[0.0002461252,0.00003259983,0.001073584,0.00003564969,0.00002052569,0.000006036131,0.00002288136,0.9909343,0.00004298989,0.005014075,0.002388749,0.0001825381],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00492752,0.00006417801,0.9931575,0.0003727002,0.0001515306,0.0007466482,0.00001711017,0.0004946438,0.00006815306],"genre_scores_gemma":[0.4663656,0.00004068549,0.5330129,0.00007082942,0.00006597854,0.0003564626,0.00006388745,0.00001624527,0.000007442977],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4614381,"threshold_uncertainty_score":0.6404706,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01732442301805016,"score_gpt":0.253662561341842,"score_spread":0.2363381383237919,"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."}}