{"id":"W4396594862","doi":"10.1109/jiot.2024.3396217","title":"Communication-Efficient and Privacy-Preserving Aggregation in Federated Learning With Adaptability","year":2024,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Key Research and Development Projects of Shaanxi Province; National Natural Science Foundation of China","keywords":"Computer science; Differential privacy; Data aggregator; Adaptability; Overhead (engineering); Information privacy; Artificial noise; Quantization (signal processing); Redundancy (engineering); Coding (social sciences); Distributed computing; Computer network; Data mining; Algorithm; Computer security; Channel (broadcasting)","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":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001694866,0.0001425196,0.0002010185,0.0003156186,0.0001065422,0.0007715255,0.009218827,0.0000885448,0.00001271997],"category_scores_gemma":[0.005587737,0.0001167369,0.00003552092,0.0004739329,0.0001426361,0.001379148,0.01424936,0.001142495,0.000002980951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000157471,"about_ca_system_score_gemma":0.00009075653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002358288,"about_ca_topic_score_gemma":0.00002331439,"domain_scores_codex":[0.9984112,0.0002023106,0.0004656173,0.0003279936,0.0003616563,0.0002312179],"domain_scores_gemma":[0.9975002,0.0003592115,0.0002416258,0.001695396,0.0001478532,0.0000556788],"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":[0.0005724162,0.001022829,0.07244889,0.001431495,0.0007776626,0.0008718402,0.05128251,0.02001407,0.01977968,0.01237511,0.04395721,0.7754663],"study_design_scores_gemma":[0.000227368,0.0001125412,0.00140851,0.001310937,0.000005587742,0.0003002562,0.0001491796,0.970735,0.006337951,0.01881053,0.0004674483,0.0001346993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6305858,0.001430637,0.3600441,0.007137625,0.0001935467,0.00009660167,4.981848e-7,0.0002239597,0.0002872176],"genre_scores_gemma":[0.891701,0.0001739993,0.1080384,0.00002531425,0.00001124443,0.0000032311,0.000001026709,0.00001083771,0.00003485256],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9507209,"threshold_uncertainty_score":0.9961418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02128142179680075,"score_gpt":0.2686820630083711,"score_spread":0.2474006412115703,"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."}}