{"id":"W3205260830","doi":"10.1109/jsac.2021.3118352","title":"Optimizing Federated Learning in Distributed Industrial IoT: A Multi-Agent Approach","year":2021,"lang":"en","type":"article","venue":"IEEE Journal on Selected Areas in Communications","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":288,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor; University of Waterloo","funders":"National Key Research and Development Program of China; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Internet of Things; Distributed computing; Distributed learning; Artificial intelligence; World Wide Web","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":["metaresearch","open_science","research_integrity"],"consensus_categories":["open_science"],"category_scores_codex":[0.001040728,0.000232286,0.0003445701,0.0005376818,0.00062324,0.0006176564,0.01744532,0.0002882353,0.000007307045],"category_scores_gemma":[0.02463537,0.0002442254,0.00006638912,0.004332922,0.00009748631,0.0004337665,0.01446906,0.004119638,0.00001015779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007331217,"about_ca_system_score_gemma":0.0006960395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004544764,"about_ca_topic_score_gemma":0.0001944719,"domain_scores_codex":[0.9965007,0.001393378,0.0007603388,0.0004424123,0.0003750869,0.0005281111],"domain_scores_gemma":[0.9928238,0.0007319913,0.0003474639,0.005548987,0.0004268548,0.0001209101],"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":[0.0004332692,0.0254967,0.126001,0.0001000893,0.001194517,0.002628983,0.006883753,0.382053,0.04203445,0.008098418,0.1346902,0.2703857],"study_design_scores_gemma":[0.00223768,0.0000749,0.004593079,0.0003248368,0.000008985006,0.0003394911,0.0002982754,0.9848983,0.002527195,0.001718171,0.002596426,0.0003826726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09811738,0.001202411,0.8587138,0.03887844,0.0006128039,0.0005075549,0.0000384566,0.0009903053,0.0009388205],"genre_scores_gemma":[0.6340483,0.0005284476,0.3651147,0.00009964485,0.00003277226,0.00003652041,0.0001026095,0.00001769208,0.00001930255],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6028453,"threshold_uncertainty_score":0.9981779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1191208882038356,"score_gpt":0.3230193121981485,"score_spread":0.203898423994313,"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."}}