{"id":"W4393152358","doi":"10.1609/aaai.v38i21.30557","title":"Adapted Weighted Aggregation in Federated Learning","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Federated 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":[0.007473359,0.0009226948,0.001777443,0.001213092,0.001023379,0.002031445,0.002881996,0.001486902,0.0009735479],"category_scores_gemma":[0.01308708,0.0004199278,0.0008930626,0.002105629,0.001223258,0.004441446,0.002862578,0.001740163,0.0003059761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001471816,"about_ca_system_score_gemma":0.001469829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00295586,"about_ca_topic_score_gemma":0.002588584,"domain_scores_codex":[0.9961015,0.001581326,0.000247982,0.000852345,0.0008450683,0.0003717534],"domain_scores_gemma":[0.994662,0.001894771,0.0003317114,0.001876125,0.001016002,0.0002192943],"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":[0.0004345609,0.0003136166,0.002596096,0.00009358471,0.0002436301,0.0001535115,0.0001856926,0.7487107,0.002247025,0.03709548,0.002338315,0.2055878],"study_design_scores_gemma":[0.00001064506,0.00003759765,0.0001388439,0.000006346123,0.00001409037,0.0000359627,0.0000143374,0.9676191,0.001228288,0.03029846,0.0005893516,0.000007034433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02290448,0.0002075294,0.9751442,0.0001432037,0.00005422775,0.00004588427,0.00004933774,0.0007310286,0.0007202037],"genre_scores_gemma":[0.7333062,0.0001717626,0.2636526,0.0002494034,0.00007348364,0.0001326345,0.0002296619,0.0001154612,0.002068764],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007473359,"threshold_uncertainty_score":0.03952342,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07389633450015325,"score_gpt":0.3025962828729584,"score_spread":0.2286999483728051,"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."}}