{"id":"W4388116613","doi":"10.1109/mass58611.2023.00013","title":"FedSaw: Communication-Efficient Cross-Silo Federated Learning with Adaptive Compression","year":2023,"lang":"en","type":"article","venue":"","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Silo; Computer science; Compression (physics); Data compression; Artificial intelligence; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00386225,0.001526078,0.001711179,0.001073612,0.0009017036,0.001603279,0.004267483,0.00195413,0.002311723],"category_scores_gemma":[0.01170949,0.0005633848,0.0007830641,0.001335318,0.00138743,0.004093348,0.004197825,0.002352357,0.001064095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001078876,"about_ca_system_score_gemma":0.002191468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003467547,"about_ca_topic_score_gemma":0.003742344,"domain_scores_codex":[0.9975638,0.0006980997,0.000194285,0.0005868758,0.0006406507,0.0003163129],"domain_scores_gemma":[0.9957009,0.001742893,0.0002671141,0.001442846,0.000630894,0.0002154065],"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":[0.00108383,0.0006467311,0.003525618,0.0002286334,0.0001795393,0.0003577727,0.0002821948,0.47861,0.007858593,0.01014673,0.01593162,0.4811487],"study_design_scores_gemma":[0.00005674803,0.00009408234,0.0001927563,0.00001178641,0.00001254718,0.00006462412,0.00003193118,0.9871696,0.002606444,0.008635022,0.001111042,0.00001341962],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04065387,0.001048979,0.9410688,0.0006046443,0.0001764901,0.00020472,0.0003228365,0.01356821,0.002351484],"genre_scores_gemma":[0.7157639,0.0003108711,0.2764655,0.0008786481,0.0001201602,0.0004526092,0.001668712,0.0004571795,0.003882525],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004267483,"threshold_uncertainty_score":0.02042574,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04295426468069081,"score_gpt":0.3040631710101932,"score_spread":0.2611089063295024,"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."}}