{"id":"W4280648662","doi":"10.1109/wcnc51071.2022.9771994","title":"Probabilistic Node Selection for Federated Learning with Heterogeneous Data in Mobile Edge","year":2022,"lang":"en","type":"article","venue":"2022 IEEE Wireless Communications and Networking Conference (WCNC)","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Node (physics); Probabilistic logic; Independent and identically distributed random variables; Enhanced Data Rates for GSM Evolution; Convergence (economics); Selection (genetic algorithm); Distributed learning; Distributed computing; Local optimum; Artificial intelligence; Random variable; Mathematics","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":["sts","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0008931455,0.0001974184,0.0002630427,0.0001621591,0.001516686,0.0003583147,0.01761301,0.00007144197,0.000009256626],"category_scores_gemma":[0.000255848,0.0002082769,0.00002112451,0.0009719807,0.0001787501,0.0003898775,0.04240173,0.0008155438,8.385028e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001481754,"about_ca_system_score_gemma":0.0001951712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001493391,"about_ca_topic_score_gemma":0.001163184,"domain_scores_codex":[0.9979061,0.0004023835,0.0003327079,0.0007239948,0.0002273932,0.000407381],"domain_scores_gemma":[0.9920627,0.0005449253,0.0002224554,0.007017241,0.0001035457,0.00004906342],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001568968,0.0008558435,0.01630617,0.0001555829,0.0001783124,0.0000189014,0.001219097,0.02483263,0.001741324,0.005940617,0.007413045,0.9411816],"study_design_scores_gemma":[0.0003708532,0.0002302464,0.00005998369,0.00006247749,0.00001150778,0.00005115549,0.0001548349,0.9773435,0.00005645267,0.003510866,0.01788871,0.0002594135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2821078,0.004809654,0.6990288,0.008328043,0.0006606298,0.002858274,0.0001628215,0.001624643,0.0004193767],"genre_scores_gemma":[0.9624238,0.001333934,0.03457419,0.00006682354,0.00002623106,0.001138794,0.000380249,0.00002349238,0.00003250617],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9525109,"threshold_uncertainty_score":0.9997832,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0745433781035592,"score_gpt":0.2988618241581452,"score_spread":0.224318446054586,"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."}}