{"id":"W4398765190","doi":"10.1109/tnsm.2024.3405004","title":"CRS-FL: Conditional Random Sampling for Communication-Efficient and Privacy-Preserving Federated Learning","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Network and Service Management","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Federated learning; Sampling (signal processing); Artificial intelligence; Telecommunications","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":[0.005846825,0.0009964885,0.001538462,0.000996732,0.0008351452,0.001399811,0.003055897,0.001356466,0.001902055],"category_scores_gemma":[0.01815764,0.0004444134,0.001079342,0.001250516,0.001533394,0.002757256,0.003046754,0.002304,0.0005158812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001300269,"about_ca_system_score_gemma":0.002657402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002436744,"about_ca_topic_score_gemma":0.002642333,"domain_scores_codex":[0.9946141,0.002345145,0.0002571461,0.001086297,0.00130412,0.0003932169],"domain_scores_gemma":[0.9912833,0.004888635,0.0005467413,0.001948952,0.00101779,0.0003145182],"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":[0.0007548819,0.0003239351,0.00331128,0.0003138032,0.0001991637,0.0002396199,0.0002618555,0.5677804,0.007375093,0.07049143,0.007022359,0.3419261],"study_design_scores_gemma":[0.0000279345,0.00006763655,0.0001431445,0.000009866803,0.0000133367,0.0000754274,0.00001854732,0.9768148,0.001998401,0.01995592,0.000862262,0.00001266582],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00560476,0.0001398486,0.9926859,0.0001653154,0.0000245724,0.00004682171,0.00005588375,0.0007813873,0.0004956106],"genre_scores_gemma":[0.64798,0.0002767243,0.3476854,0.0006694109,0.0001157456,0.0002979983,0.0005445998,0.0002109096,0.002219153],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005846825,"threshold_uncertainty_score":0.03092134,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0312840824549279,"score_gpt":0.2788177495539977,"score_spread":0.2475336670990698,"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."}}