{"id":"W4320011078","doi":"10.1109/iccspa55860.2022.10019204","title":"DSFL: Dynamic Sparsification for Federated Learning","year":2022,"lang":"en","type":"article","venue":"","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Bottleneck; Information bottleneck method; Key (lock); Similarity (geometry); Kernel (algebra); Theoretical computer science; Federated learning; Artificial intelligence; Machine learning; Distributed computing; Image (mathematics); Cluster analysis; Mathematics","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":[0.002071433,0.0009313125,0.001010798,0.0005680067,0.0005192942,0.001061422,0.001856721,0.001220431,0.002433071],"category_scores_gemma":[0.006775781,0.0003965402,0.0007348725,0.0006776898,0.001232079,0.002323535,0.003225235,0.002029788,0.000868194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008631019,"about_ca_system_score_gemma":0.001329764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002013227,"about_ca_topic_score_gemma":0.002244539,"domain_scores_codex":[0.9984915,0.000519704,0.0001032305,0.0002972813,0.0004583997,0.0001299326],"domain_scores_gemma":[0.9972494,0.001194308,0.0001922072,0.0008920051,0.0003529135,0.0001190323],"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":[0.0003066927,0.0001425528,0.0008275424,0.0001177749,0.00006948687,0.0001645836,0.0001574925,0.693558,0.005794172,0.04838245,0.006137122,0.2443421],"study_design_scores_gemma":[0.000009709447,0.00002089662,0.0000411997,0.00000561283,0.000002714309,0.00002600887,0.00001061161,0.9816741,0.001769721,0.01532836,0.001105663,0.000005386744],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004346873,0.00007208761,0.9936514,0.0001277261,0.00002030633,0.00003151389,0.00005994378,0.0009543406,0.0007357089],"genre_scores_gemma":[0.3897345,0.0002463909,0.6049603,0.0003617921,0.00009099985,0.0003096905,0.0007138111,0.0002692182,0.003313247],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002433071,"threshold_uncertainty_score":0.01095486,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03524959394714611,"score_gpt":0.282901786440278,"score_spread":0.2476521924931319,"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."}}