{"id":"W3128646026","doi":"10.1109/tnse.2021.3056655","title":"FLAS: Computation and Communication Efficient Federated Learning via Adaptive Sampling","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Network Science and Engineering","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Computer science; Correctness; Federated learning; Overhead (engineering); Usability; Convergence (economics); Computation; Distributed computing; Filter (signal processing); Distributed learning; Adaptive sampling; Statistic; Artificial intelligence; Machine learning; Data mining; Human–computer interaction; Algorithm","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":[],"consensus_categories":[],"category_scores_codex":[0.0005702165,0.0001159431,0.0001102461,0.0001365388,0.0008252206,0.0003534199,0.001448007,0.00005382239,9.756089e-7],"category_scores_gemma":[0.0002927524,0.0001260315,0.00001505964,0.001340244,0.0001341008,0.0004861589,0.0004148484,0.0003445401,0.000002152616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008063898,"about_ca_system_score_gemma":0.00006932464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009852319,"about_ca_topic_score_gemma":0.000005771419,"domain_scores_codex":[0.9988723,0.00003138471,0.0001495838,0.0003973067,0.0002574839,0.0002919376],"domain_scores_gemma":[0.9988528,0.0002233235,0.00003962548,0.0006715223,0.0001411572,0.00007158249],"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":[0.000001742758,0.00001220695,0.000004683125,0.000005974304,0.000006207144,0.000001997472,0.00008797672,0.9389699,0.004252065,0.0002051805,0.00004452869,0.05640758],"study_design_scores_gemma":[0.000105715,0.00003324392,0.0002489969,0.00008374877,0.000004437534,0.00003020966,0.00005011321,0.9944378,0.004093814,0.0007187148,0.00005904266,0.00013421],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0363186,0.0002866424,0.9618769,0.0007756306,0.000217223,0.00007282919,7.530693e-7,0.0004053663,0.00004606763],"genre_scores_gemma":[0.7450736,0.0001376195,0.2547341,0.00002915061,0.000008805292,0.000007736754,7.220002e-7,0.000005426099,0.000002838899],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.708755,"threshold_uncertainty_score":0.6347013,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02387405128044365,"score_gpt":0.2452208174266214,"score_spread":0.2213467661461777,"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."}}