{"id":"W4405270867","doi":"10.1109/tpds.2024.3515804","title":"UMPIPE: Unequal Microbatches-Based Pipeline Parallelism for Deep Neural Network Training","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Parallel and Distributed Systems","topic":"Neural Networks and Reservoir Computing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Pipeline (software); Parallelism (grammar); Parallel computing; Artificial neural network; Training (meteorology); Data parallelism; Computer architecture; Artificial intelligence; Operating system","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":[0.0006729336,0.0008612687,0.0005710152,0.0004540198,0.0005618481,0.0006309478,0.00210834,0.0007582476,0.004490362],"category_scores_gemma":[0.001954128,0.0004200992,0.0006345045,0.0006280904,0.000565235,0.001746035,0.001456037,0.001621334,0.0008176538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001055498,"about_ca_system_score_gemma":0.002441989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006093125,"about_ca_topic_score_gemma":0.01201649,"domain_scores_codex":[0.9996421,0.00005956386,0.00002158635,0.0000933666,0.0001204411,0.00006285194],"domain_scores_gemma":[0.999535,0.0001892774,0.00003886808,0.0001020888,0.00008904012,0.00004584284],"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":[0.0003521804,0.0002952203,0.001901524,0.000207068,0.00008819876,0.0001692852,0.0001396529,0.5467594,0.01813855,0.01839062,0.01349227,0.400066],"study_design_scores_gemma":[0.00003912585,0.00007398938,0.0001392627,0.000006994277,0.000009525841,0.00002619341,0.00001269871,0.9875236,0.004964964,0.005143501,0.002052364,0.000007792083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04385469,0.0004834256,0.9414822,0.0003686484,0.0001045912,0.0001250231,0.000202146,0.008369882,0.005009438],"genre_scores_gemma":[0.3520509,0.0002526198,0.6409606,0.000332332,0.00003629812,0.0003128865,0.0007218567,0.0007006317,0.004631911],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006093125,"threshold_uncertainty_score":0.0150218,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03361677045423552,"score_gpt":0.259957126064931,"score_spread":0.2263403556106955,"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."}}