{"id":"W4410882914","doi":"10.1016/j.sysarc.2025.103460","title":"FedMQ+: Towards efficient heterogeneous federated learning with multi-grained quantization","year":2025,"lang":"en","type":"article","venue":"Journal of Systems Architecture","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Key Technology Research and Development Program of Shandong; Postdoctoral Innovation Project of Shandong Province; Natural Science Foundation of Shandong Province","keywords":"Computer science; Federated learning; Quantization (signal processing); Distributed computing; Theoretical computer science; Artificial intelligence; Computer architecture; 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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0007349243,0.0002214306,0.0003980228,0.0005450668,0.0002618747,0.0004563401,0.006862691,0.0001448261,0.000001347602],"category_scores_gemma":[0.004264679,0.0001512184,0.0000903649,0.0009558914,0.00006542033,0.0001484073,0.005462892,0.0007317761,0.000002549491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001421534,"about_ca_system_score_gemma":0.0002370416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003384381,"about_ca_topic_score_gemma":0.00001260188,"domain_scores_codex":[0.9980022,0.0002607591,0.000580632,0.0003190437,0.000519746,0.0003176378],"domain_scores_gemma":[0.9972904,0.0001191939,0.0005993913,0.001525923,0.000389619,0.00007552493],"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":[0.000188994,0.0002563644,0.002526115,0.0003973401,0.0004954693,0.0005726237,0.0007744414,0.9257422,0.01020886,0.0009073935,0.006024124,0.05190605],"study_design_scores_gemma":[0.001568371,0.0005164567,0.0008591177,0.001184064,0.00003286178,0.001485909,0.0001844131,0.9836771,0.005257424,0.0009650205,0.003955627,0.0003136472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09797184,0.0008990531,0.8946254,0.005252416,0.000650476,0.0002243523,0.000002641495,0.0002592296,0.0001145646],"genre_scores_gemma":[0.8985026,0.0000160489,0.1012639,0.00005502205,0.00005116321,0.000005182064,0.000002219118,0.00001386408,0.00008999713],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8005308,"threshold_uncertainty_score":0.9985107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01602227068205336,"score_gpt":0.2619340151175543,"score_spread":0.245911744435501,"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."}}