{"id":"W4401408935","doi":"10.1145/3673038.3673154","title":"Murmuration: On-the-fly DNN Adaptation for SLO-Aware Distributed Inference in Dynamic Edge Environments","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Inference; Latency (audio); Distributed computing; Personalization; Edge computing; Adaptation (eye); Artificial neural network; Enhanced Data Rates for GSM Evolution; Edge device; Reinforcement learning; Bandwidth (computing); Artificial intelligence; Cloud computing; Machine learning; Computer network","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":[],"consensus_categories":[],"category_scores_codex":[0.00009283877,0.0001139892,0.00007572458,0.00005415562,0.0001129808,0.0001182266,0.0004356901,0.0000385581,0.00001536059],"category_scores_gemma":[0.00004307992,0.00008746048,0.00003514762,0.0004671004,0.00003021638,0.000398326,0.00008436074,0.0001180303,0.000115783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001421944,"about_ca_system_score_gemma":0.00003763102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002522634,"about_ca_topic_score_gemma":0.00004325996,"domain_scores_codex":[0.9990598,0.00002738759,0.0002000263,0.0003781198,0.0001470128,0.0001876299],"domain_scores_gemma":[0.9987002,0.000823769,0.0000366874,0.0003872078,0.00001435579,0.00003780324],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001139776,0.0001094286,0.00006557957,0.00002382502,0.00001512729,0.000006814033,0.0004701887,0.1419177,0.001064435,0.7175407,0.002514679,0.1362601],"study_design_scores_gemma":[0.00009448675,0.00004070763,0.0007597963,0.00002423963,0.000002142005,0.000001098923,0.00002472957,0.9640758,0.0004435517,0.02341245,0.01101289,0.000108095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002054537,0.00004568204,0.9905497,0.006342278,0.000144435,0.0005684498,0.00002676341,0.0001445079,0.0001236138],"genre_scores_gemma":[0.988288,0.00002656902,0.01021566,0.000306758,0.00002973262,0.0004797821,0.00008451609,0.000008982043,0.0005599509],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9862335,"threshold_uncertainty_score":0.3566535,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03041338073792147,"score_gpt":0.2899150118096457,"score_spread":0.2595016310717242,"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."}}