{"id":"W4283204791","doi":"10.1109/infocom48880.2022.9796896","title":"Distributed Inference with Deep Learning Models across Heterogeneous Edge Devices","year":2022,"lang":"en","type":"article","venue":"IEEE INFOCOM 2022 - IEEE Conference on Computer Communications","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Inference; Computer science; Deep learning; Directed acyclic graph; Artificial intelligence; Approximate inference; Enhanced Data Rates for GSM Evolution; Edge device; Machine learning; Theoretical computer science; Algorithm","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":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0007345171,0.0005716181,0.0005805229,0.0002749873,0.003715658,0.001076324,0.008455186,0.0001168338,0.00002380168],"category_scores_gemma":[0.0000194525,0.0005980557,0.0001865772,0.001454205,0.0003834035,0.000960494,0.0039634,0.00192209,0.00008629909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003125691,"about_ca_system_score_gemma":0.0003440733,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001311227,"about_ca_topic_score_gemma":0.0001040776,"domain_scores_codex":[0.9954095,0.0009041892,0.0008116144,0.0009603912,0.0008851344,0.001029145],"domain_scores_gemma":[0.9938812,0.0009162073,0.0005695618,0.003864421,0.0004708463,0.0002977522],"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":[0.00006992116,0.000901663,0.001713525,0.00005143839,0.0002566453,0.00008371075,0.01276166,0.8040525,0.0002112745,0.02307484,0.002818527,0.1540043],"study_design_scores_gemma":[0.0006689281,0.000611093,0.0003857666,0.00007830738,0.00001707736,0.0001108344,0.0001645152,0.9748324,0.0001484209,0.001970538,0.02023425,0.000777896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0410095,0.0002065711,0.9508042,0.001464186,0.00355484,0.0006062259,0.0000245978,0.0008840273,0.001445801],"genre_scores_gemma":[0.9713486,0.00008947949,0.02649637,0.0009972973,0.0003700487,0.0003919663,0.0001598223,0.00004815205,0.00009827833],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9303391,"threshold_uncertainty_score":0.9999607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08018509552167943,"score_gpt":0.3042089167860083,"score_spread":0.2240238212643289,"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."}}