{"id":"W4225926344","doi":"10.1109/tnse.2022.3169117","title":"Federated Learning Meets Multi-Objective Optimization","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Network Science and Engineering","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":146,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Hyperparameter; Robustness (evolution); Artificial intelligence; Convergence (economics); Pareto principle; Machine learning; Information retrieval; Mathematics; Mathematical optimization","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"],"consensus_categories":[],"category_scores_codex":[0.0007079213,0.0001229823,0.0001009682,0.0002603062,0.001575409,0.0002347824,0.003423136,0.00003342089,0.00001047064],"category_scores_gemma":[0.0003218287,0.0001361775,0.00002096314,0.002278404,0.00008368343,0.0008073942,0.0006611847,0.0004823679,0.000001995114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001882223,"about_ca_system_score_gemma":0.00008984821,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001308242,"about_ca_topic_score_gemma":0.0000024919,"domain_scores_codex":[0.9985842,0.00003053543,0.0001309787,0.0004627806,0.000401035,0.0003904794],"domain_scores_gemma":[0.9989828,0.00008330617,0.00003838782,0.0007622709,0.00006458446,0.00006863575],"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":[0.000002109584,0.00001752963,0.000004644362,0.000002293884,0.000005404945,0.000003591702,0.00005947872,0.988259,0.0007840548,0.00005323159,0.0002622255,0.01054642],"study_design_scores_gemma":[0.0001398756,0.0000750876,0.0000436425,0.00001149839,0.000002945153,0.00002122557,0.00004786326,0.9975749,0.00152948,0.00006336634,0.0003355463,0.0001546042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002735296,0.00006312827,0.9944207,0.0009969512,0.0007969291,0.0001161907,0.000002050526,0.0008086052,0.00006016847],"genre_scores_gemma":[0.775703,0.00004718622,0.2241063,0.00005363749,0.00001325945,0.0000487775,6.016427e-7,0.000008716892,0.00001853926],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7729677,"threshold_uncertainty_score":0.9997244,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01586424113468361,"score_gpt":0.2264590596634469,"score_spread":0.2105948185287633,"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."}}