{"id":"W4402302364","doi":"10.1109/jsyst.2024.3450883","title":"Communication-Efficient Federated Learning for Large-Scale Multiagent Systems in ISAC: Data Augmentation With Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"IEEE Systems Journal","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Exfo Electro-Optical Engineering (Canada)","funders":"National Natural Science Foundation of China","keywords":"Reinforcement learning; Computer science; Scale (ratio); Multi-agent system; Distributed computing; Human–computer interaction; 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":[0.001915414,0.0009476777,0.001302646,0.0003072731,0.0006328087,0.001157397,0.001488127,0.001145142,0.001271701],"category_scores_gemma":[0.004573595,0.0004338202,0.0005859542,0.0005535051,0.001184669,0.001727641,0.002149034,0.002566312,0.0002564258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009510725,"about_ca_system_score_gemma":0.001564822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004460793,"about_ca_topic_score_gemma":0.003746479,"domain_scores_codex":[0.9991087,0.000283218,0.00004694576,0.0002621218,0.0001610831,0.000137918],"domain_scores_gemma":[0.9973962,0.001448658,0.0002861139,0.0003543425,0.0003604295,0.0001542783],"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":[0.0001265804,0.00008524545,0.0009423757,0.00007446517,0.00005281338,0.0001284835,0.00009572483,0.9299124,0.001854334,0.01064994,0.001454366,0.05462326],"study_design_scores_gemma":[0.000004227867,0.00001782108,0.00005070719,0.000002446869,0.000003212253,0.00001002136,0.000006038613,0.9972427,0.0002615819,0.002263928,0.0001344711,0.000002879742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01992289,0.0003136178,0.977435,0.0002992505,0.0000601629,0.00004567211,0.00003341909,0.0004241437,0.00146585],"genre_scores_gemma":[0.9181801,0.0002237003,0.07925755,0.0002608325,0.00005881055,0.0001383172,0.0001005577,0.00004648851,0.001733616],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004460793,"threshold_uncertainty_score":0.01012975,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05300090717258719,"score_gpt":0.3173722239504397,"score_spread":0.2643713167778525,"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."}}