{"id":"W4390604537","doi":"10.1109/lcomm.2024.3350378","title":"Fair Wireless Federated Learning Through the Identification of a Common Descent Direction","year":2024,"lang":"en","type":"article","venue":"IEEE Communications Letters","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Descent (aeronautics); Wireless; Identification (biology); Minification; Federated learning; Stochastic gradient descent; Gradient descent; Wireless network; Algorithm; Data mining; Computer network; Artificial intelligence; Machine learning; Telecommunications; Artificial neural network; World Wide Web","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":[0.0006281191,0.0001220184,0.0001295531,0.0001203964,0.0005648004,0.0004344738,0.01987881,0.00006633935,0.000001684529],"category_scores_gemma":[0.0009414505,0.0001023576,0.00006512331,0.001085029,0.0003275845,0.0007887394,0.01297014,0.0005747259,0.00003743079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001351844,"about_ca_system_score_gemma":0.00003610419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002632226,"about_ca_topic_score_gemma":0.0000529601,"domain_scores_codex":[0.9984459,0.0003969555,0.0004478731,0.0002960369,0.0002326041,0.0001806367],"domain_scores_gemma":[0.9898849,0.0005483674,0.0001875826,0.009288791,0.00007473915,0.0000156631],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007117652,0.0002796252,0.0005700287,0.0001411355,0.0002345523,0.00000690291,0.003514095,0.001300714,0.5384629,0.02707914,0.2439329,0.184471],"study_design_scores_gemma":[0.0001093069,0.00002317808,0.0009248215,0.0002113693,0.00002838918,0.00002223215,0.0002393034,0.9019129,0.06086553,0.01423505,0.0211896,0.0002383268],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05349885,0.0009165409,0.7344939,0.2085742,0.0005547132,0.0002684472,0.000006903437,0.001361354,0.0003251624],"genre_scores_gemma":[0.978565,0.0004993243,0.02042909,0.0003382172,0.00001675879,0.00008095609,0.00002768745,0.00001433468,0.00002865201],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9250661,"threshold_uncertainty_score":0.9950128,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04716151527323351,"score_gpt":0.308321994918857,"score_spread":0.2611604796456235,"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."}}