{"id":"W3088682211","doi":"10.1109/comst.2021.3090430","title":"Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challenges","year":2021,"lang":"en","type":"preprint","venue":"IEEE Communications Surveys & Tutorials","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"National Research Foundation of Korea","keywords":"Computer science; Federated learning; Scalability; Cloud computing; Software deployment; Artificial intelligence; Internet of Things; Machine learning; Robustness (evolution); World Wide Web; Software engineering; Database","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":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.009106843,0.0003717545,0.0009779298,0.0001959854,0.0003213058,0.001171249,0.06228365,0.0004730835,0.000007855733],"category_scores_gemma":[0.04046106,0.0004065382,0.00009476667,0.0003301861,0.0003449394,0.001383182,0.3021164,0.001057422,0.000002307419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001871819,"about_ca_system_score_gemma":0.000547418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006737984,"about_ca_topic_score_gemma":0.0005345165,"domain_scores_codex":[0.9937316,0.003622795,0.001002956,0.001034627,0.000267121,0.0003408823],"domain_scores_gemma":[0.9779259,0.003420149,0.001227983,0.01631432,0.001037301,0.00007432622],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002119081,0.0003819772,0.0002313437,0.0005451678,0.0004306404,0.000002238568,0.001069679,0.0000735136,0.0005729817,0.006488222,0.01892095,0.9712621],"study_design_scores_gemma":[0.001306673,0.0002393931,0.000462007,0.002014043,0.0000901411,0.00001284656,0.0006913783,0.08451677,0.009802416,0.09409059,0.8053779,0.001395829],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004004303,0.07835142,0.8933413,0.01766712,0.004764807,0.002682617,0.00009391997,0.0006465267,0.002051823],"genre_scores_gemma":[0.08938419,0.1987824,0.7093407,0.00004834362,0.00009739128,0.001645967,0.0005751662,0.00004520299,0.00008066645],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9698663,"threshold_uncertainty_score":0.9998657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2100094110369333,"score_gpt":0.3652114053117794,"score_spread":0.1552019942748461,"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."}}