{"id":"W4416798297","doi":"10.1109/tvt.2025.3638365","title":"Multi-Block ADMM for Efficient Model Pruning and Link Scheduling in Decentralized Learning","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Vehicular Technology","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Scheduling (production processes); Pruning; Consistency (knowledge bases); Job shop scheduling; Convergence (economics); Data modeling; Multicast","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":[0.001960508,0.0009096933,0.001357798,0.0004157378,0.0006598721,0.0007977556,0.001725605,0.0009577652,0.001778839],"category_scores_gemma":[0.004086534,0.0005665003,0.0005054657,0.0007407304,0.000785478,0.001613631,0.001386618,0.002226789,0.0004487945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008210642,"about_ca_system_score_gemma":0.002086872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003070716,"about_ca_topic_score_gemma":0.00480433,"domain_scores_codex":[0.9991731,0.0003135302,0.00003666334,0.0001655172,0.0002267799,0.00008434671],"domain_scores_gemma":[0.998456,0.0008166746,0.0001716759,0.0002488993,0.0002384168,0.00006840496],"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":[0.00005515594,0.00004545865,0.0002266188,0.00006211808,0.00002475004,0.00003731948,0.00003980242,0.9456579,0.00131402,0.01156732,0.001201533,0.03976794],"study_design_scores_gemma":[0.00000606872,0.000009053895,0.0000168555,0.000001599333,0.000001734921,0.000004223132,0.000002204827,0.9969935,0.0001911005,0.002590856,0.0001813433,0.000001368145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003092829,0.00007725163,0.9961133,0.00006813234,0.00001517493,0.00001563261,0.00001971037,0.000170573,0.0004273715],"genre_scores_gemma":[0.5393056,0.0002312903,0.4569172,0.0002427084,0.0001089044,0.0002842711,0.0003167635,0.0001511003,0.002442097],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003070716,"threshold_uncertainty_score":0.01036823,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02620495145216118,"score_gpt":0.2922477044338427,"score_spread":0.2660427529816815,"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."}}