{"id":"W4413145682","doi":"10.1109/cvpr52734.2025.02345","title":"Beyond Local Sharpness: Communication-Efficient Global Sharpness-aware Minimization for Federated Learning","year":2025,"lang":"en","type":"article","venue":"","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute","funders":"","keywords":"Computer science; Federated learning; Minification; Artificial intelligence; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00236418,0.001596389,0.001364329,0.0007811848,0.0007695712,0.001803542,0.00307718,0.002326789,0.004324881],"category_scores_gemma":[0.008541996,0.0005948599,0.001088079,0.0007626485,0.001502423,0.00301639,0.003469159,0.002959433,0.001463751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001413668,"about_ca_system_score_gemma":0.001742104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004079592,"about_ca_topic_score_gemma":0.006180904,"domain_scores_codex":[0.9990205,0.0002282103,0.00005467167,0.0002643458,0.0002959073,0.0001363154],"domain_scores_gemma":[0.9975823,0.0009854838,0.0001684641,0.0007739534,0.0003457087,0.0001440042],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002863352,0.0002130682,0.001422913,0.0001554339,0.00008737021,0.0001452544,0.0001675191,0.7641621,0.007515525,0.01389378,0.008136227,0.2038145],"study_design_scores_gemma":[0.00001608077,0.00003795767,0.00007804299,0.00001194197,0.000006861174,0.00004013388,0.00001809177,0.9879985,0.002293452,0.008807676,0.0006835263,0.00000776018],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0161076,0.0002665418,0.9772609,0.0002814603,0.0000441246,0.00005126771,0.0001156532,0.003768675,0.002103725],"genre_scores_gemma":[0.5393386,0.0002411099,0.4518858,0.0007986227,0.00006513001,0.0001976624,0.0008458626,0.001210441,0.005416754],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004324881,"threshold_uncertainty_score":0.01446819,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02025889895914025,"score_gpt":0.2961138188053616,"score_spread":0.2758549198462213,"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."}}