{"id":"W4378965902","doi":"10.1109/tmc.2023.3268323","title":"Energy Efficient and Differentially Private Federated Learning via a Piggyback Approach","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Mobile Computing","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China; National Science Foundation","keywords":"Computer science; Additive white Gaussian noise; Wireless; Efficient energy use; Mobile device; Artificial noise; Leverage (statistics); Differential privacy; Algorithm; Telecommunications; Channel (broadcasting); Artificial intelligence; Electrical engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003965735,0.0002853598,0.0002795581,0.0004284406,0.0008613781,0.0003756341,0.004573389,0.0001552691,0.000005752539],"category_scores_gemma":[0.0001382584,0.0002861954,0.00008412436,0.00149776,0.0001075871,0.0001782224,0.001315759,0.0005777545,0.00003743048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007765942,"about_ca_system_score_gemma":0.00003226643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000349041,"about_ca_topic_score_gemma":0.000003398429,"domain_scores_codex":[0.9976333,0.0001774279,0.0003573092,0.0008871745,0.0003596061,0.0005852216],"domain_scores_gemma":[0.9973931,0.0003218708,0.0001272623,0.001993475,0.00006035254,0.0001039677],"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":[0.0000112987,0.0002040784,0.00003303188,0.00004664825,0.00006638575,0.00001983013,0.0002023994,0.4601505,0.006534853,0.0001934322,0.0005262424,0.5320113],"study_design_scores_gemma":[0.0003552684,0.0001313486,0.0001429938,0.00004998766,0.000009407911,0.00002802114,0.00003724719,0.9857006,0.01206984,0.0009436879,0.0002421463,0.000289421],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1684439,0.00003206163,0.8275889,0.0003365086,0.000448425,0.0001991173,0.00000336254,0.002844003,0.0001037866],"genre_scores_gemma":[0.9459284,0.0000461435,0.0537988,0.00004401513,0.00002671241,0.00005152056,0.000008741169,0.0000312125,0.00006446805],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7774845,"threshold_uncertainty_score":0.999959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01957542883941355,"score_gpt":0.2456093674440151,"score_spread":0.2260339386046016,"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."}}