{"id":"W4226052253","doi":"10.1109/bigdata55660.2022.10020281","title":"PMFL: Partial Meta-Federated Learning for heterogeneous tasks and its applications on real-world medical records","year":2022,"lang":"en","type":"preprint","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"Fundamental Research Funds for the Central Universities","keywords":"Computer science; Federated learning; Transfer of learning; Meta learning (computer science); Task (project management); Machine learning; Generalization; Artificial intelligence; Homogeneous; Exploit","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":[0.005617348,0.001002542,0.001139513,0.001496944,0.0009552889,0.00141394,0.002614115,0.00226035,0.001647251],"category_scores_gemma":[0.01102421,0.0004120609,0.001236042,0.001379372,0.0008547495,0.003124344,0.002620481,0.001456701,0.0005248367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001227489,"about_ca_system_score_gemma":0.002009205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003680521,"about_ca_topic_score_gemma":0.004059264,"domain_scores_codex":[0.9982469,0.0007234514,0.0001345198,0.0004379111,0.0002683064,0.000188905],"domain_scores_gemma":[0.9965102,0.001469671,0.0001902596,0.001144063,0.0004914401,0.0001943087],"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":[0.0006933011,0.0004834754,0.006185242,0.0001751386,0.0002277633,0.0002419269,0.0002527941,0.5033939,0.002866019,0.005703421,0.008904213,0.4708728],"study_design_scores_gemma":[0.00003779728,0.00005926521,0.0003762026,0.00001257617,0.0000168204,0.00008482819,0.000032468,0.9886401,0.001768169,0.008003837,0.0009586975,0.00000931082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04903661,0.0005332097,0.9430329,0.0009310658,0.0000863206,0.000158156,0.0003489488,0.004984394,0.0008883804],"genre_scores_gemma":[0.5784202,0.0001728245,0.4171147,0.0005365901,0.00007178167,0.0002657374,0.001326612,0.0002207224,0.001870812],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005617348,"threshold_uncertainty_score":0.02970773,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4329335683524456,"score_gpt":0.4114458854522562,"score_spread":0.02148768290018938,"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."}}