{"id":"W4299306302","doi":"10.1109/compsac54236.2022.00050","title":"A Mobility Forecasting Framework with Vertical Federated Learning","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Domain (mathematical analysis); Machine learning; Data mining; Artificial neural network; Artificial intelligence; Process (computing); Mobility model; Work (physics); Mobile device; Data modeling; Distributed computing; Database","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.001006446,0.0002307625,0.000337727,0.0001351001,0.00507694,0.0003178047,0.0004626682,0.00009866564,0.0005567223],"category_scores_gemma":[0.0001774109,0.00024273,0.00008951659,0.001023927,0.0005865992,0.0002158464,0.0001581573,0.0008212489,0.00001619949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001877875,"about_ca_system_score_gemma":0.0005351788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002303129,"about_ca_topic_score_gemma":0.00144633,"domain_scores_codex":[0.9971782,0.0005787035,0.0003766178,0.0007353828,0.000594973,0.0005361208],"domain_scores_gemma":[0.9978967,0.000972279,0.0001287081,0.0003275475,0.000356046,0.0003187599],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004586215,0.002592926,0.1279703,0.0003153984,0.0005361487,0.00003567904,0.06801129,0.06585906,0.00004724532,0.1393936,0.002550556,0.5922292],"study_design_scores_gemma":[0.003472718,0.002136553,0.02619971,0.0002769729,0.0006502462,0.00004347056,0.144138,0.3811076,0.00007956809,0.05679016,0.3811476,0.003957403],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1568584,0.0001043845,0.8405252,0.0006293613,0.00009565261,0.0007350862,0.00006573487,0.0003632447,0.0006229974],"genre_scores_gemma":[0.9939333,0.00002705412,0.004416679,0.0003930487,0.0002145309,0.0006359213,0.0001076959,0.00001887504,0.0002528753],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8370749,"threshold_uncertainty_score":0.9962183,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02684329357692351,"score_gpt":0.2714185664019855,"score_spread":0.244575272825062,"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."}}