{"id":"https://openalex.org/W4415116991","doi":"https://doi.org/10.3390/make7040117","title":"Learning to Partition: Dynamic Deep Neural Network Model Partitioning for Edge-Assisted Low-Latency Video Analytics","display_name":"Learning to Partition: Dynamic Deep Neural Network Model Partitioning for Edge-Assisted Low-Latency Video Analytics","publication_year":2025,"publication_date":"2025-10-13","ids":{"openalex":"https://openalex.org/W4415116991","doi":"https://doi.org/10.3390/make7040117"},"language":"en","primary_location":{"id":"doi:10.3390/make7040117","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make7040117","pdf_url":null,"source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/make7040117","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090644485","display_name":"Y. Lyu","orcid":"https://orcid.org/0000-0002-7108-2109"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yan Lyu","raw_affiliation_strings":["School of Computer Science and Engineering, Southeast University, Nanjing 211189, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing 211189, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037219155","display_name":"Likai Liu","orcid":"https://orcid.org/0009-0005-0284-6944"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Likai Liu","raw_affiliation_strings":["School of Computer Science and Engineering, Southeast University, Nanjing 211189, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing 211189, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024842018","display_name":"Xuezhi Wang","orcid":"https://orcid.org/0000-0001-7592-2358"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuezhi Wang","raw_affiliation_strings":["School of Computer Science and Engineering, University of Science and Technology, Nanjing 210094, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Science and Technology, Nanjing 210094, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101462571","display_name":"Zhiyu Fan","orcid":"https://orcid.org/0000-0003-3424-9536"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyu Fan","raw_affiliation_strings":["School of Computer Science and Engineering, Southeast University, Nanjing 211189, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing 211189, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101615378","display_name":"Jinchen Wang","orcid":"https://orcid.org/0000-0002-2691-9002"},"institutions":[{"id":"https://openalex.org/I3017770710","display_name":"China North Industries Group Corporation (China)","ror":"https://ror.org/00cwdhv97","country_code":"CN","type":"company","lineage":["https://openalex.org/I3017770710"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinchen Wang","raw_affiliation_strings":["North Information Control Research Academy Group Co., Ltd., Nanjing 211153, China"],"affiliations":[{"raw_affiliation_string":"North Information Control Research Academy Group Co., Ltd., Nanjing 211153, China","institution_ids":["https://openalex.org/I3017770710"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024496324","display_name":"Guanyu Gao","orcid":"https://orcid.org/0000-0001-8584-0532"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanyu Gao","raw_affiliation_strings":["School of Computer Science and Engineering, University of Science and Technology, Nanjing 210094, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Science and Technology, Nanjing 210094, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5090644485"],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3008539,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":"4","first_page":"117","last_page":"117"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.7297999858856201},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5195000171661377},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.47200000286102295},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4684000015258789},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.45879998803138733},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4528999924659729},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42260000109672546},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.3935000002384186},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.3788999915122986}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8600000143051147},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.7297999858856201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5199000239372253},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5195000171661377},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.47200000286102295},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4684000015258789},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.45879998803138733},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4528999924659729},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4065000116825104},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.384799987077713},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3797000050544739},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3788999915122986},{"id":"https://openalex.org/C200157131","wikidata":"https://www.wikidata.org/wiki/Q4854763","display_name":"Bandwidth allocation","level":3,"score":0.35120001435279846},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3327000141143799},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C13540734","wikidata":"https://www.wikidata.org/wiki/Q5318996","display_name":"Dynamic network analysis","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.26899999380111694},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/make7040117","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make7040117","pdf_url":null,"source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:8fc1cca8683c4ec895a3b2c33fd8250f","is_oa":true,"landing_page_url":"https://doaj.org/article/8fc1cca8683c4ec895a3b2c33fd8250f","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning and Knowledge Extraction, Vol 7, Iss 4, p 117 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/make7040117","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make7040117","pdf_url":null,"source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2618530766","https://openalex.org/W2678047256","https://openalex.org/W2792220137","https://openalex.org/W2887117815","https://openalex.org/W2919115771","https://openalex.org/W2920031528","https://openalex.org/W2949628230","https://openalex.org/W2960833983","https://openalex.org/W2965289829","https://openalex.org/W3043914740","https://openalex.org/W3044591330","https://openalex.org/W3047565185","https://openalex.org/W3049640275","https://openalex.org/W3100229168","https://openalex.org/W3102767875","https://openalex.org/W3110777925","https://openalex.org/W3120615301","https://openalex.org/W3134255974","https://openalex.org/W3204676010","https://openalex.org/W3206194624","https://openalex.org/W4200337351","https://openalex.org/W4236099117","https://openalex.org/W4283204791","https://openalex.org/W4285047166","https://openalex.org/W4285197124","https://openalex.org/W4288084599","https://openalex.org/W4290097411","https://openalex.org/W4387968598","https://openalex.org/W4397026267","https://openalex.org/W4399990058","https://openalex.org/W4409561031","https://openalex.org/W4411621296","https://openalex.org/W4411949274"],"related_works":[],"abstract_inverted_index":{"In":[0],"edge-assisted":[1],"low-latency":[2],"video":[3,97],"analytics,":[4],"a":[5,49,75,81,88,96,106,129],"critical":[6,31],"challenge":[7],"is":[8,159],"balancing":[9],"on-device":[10],"inference":[11],"latency":[12,145],"against":[13],"the":[14,112,122,160,167],"high":[15,65],"bandwidth":[16],"costs":[17,67],"and":[18,29,60,68,144,182],"network":[19,59],"delays":[20],"of":[21],"offloading.":[22],"Ineffectively":[23],"managing":[24],"this":[25,176],"trade-off":[26],"degrades":[27],"performance":[28],"hinders":[30],"applications":[32],"like":[33],"autonomous":[34],"systems.":[35],"Existing":[36],"solutions":[37],"often":[38],"rely":[39],"on":[40,87,174],"static":[41],"partitioning":[42,77,178],"or":[43],"greedy":[44],"algorithms":[45],"that":[46,91],"optimize":[47],"for":[48,117,128],"single":[50],"frame.":[51],"These":[52],"myopic":[53],"approaches":[54],"adapt":[55],"poorly":[56],"to":[57,64,93,109,180],"dynamic":[58,177],"workload":[61],"conditions,":[62],"leading":[63],"long-term":[66,131],"significant":[69],"frame":[70,119,149],"drops.":[71],"This":[72],"paper":[73],"introduces":[74],"novel":[76],"technique":[78],"driven":[79],"by":[80,120,166],"Deep":[82,99],"Reinforcement":[83],"Learning":[84],"(DRL)":[85],"agent":[86,104],"local":[89],"device":[90],"learns":[92,105],"dynamically":[94,110],"partition":[95],"analytics":[98],"Neural":[100],"Network":[101],"(DNN).":[102],"The":[103,156],"farsighted":[107],"policy":[108],"select":[111],"optimal":[113],"DNN":[114],"split":[115],"point":[116],"each":[118],"observing":[121],"holistic":[123],"system":[124,142],"state.":[125],"By":[126],"optimizing":[127],"cumulative":[130],"reward,":[132],"our":[133,152],"method":[134],"significantly":[135],"outperforms":[136],"competitor":[137],"methods,":[138],"demonstrably":[139],"reducing":[140],"overall":[141],"cost":[143],"while":[146],"nearly":[147],"eliminating":[148],"drops":[150],"in":[151],"real-world":[153],"testbed":[154],"evaluation.":[155],"primary":[157],"limitation":[158],"initial":[161],"offline":[162],"training":[163],"phase":[164],"required":[165],"DRL":[168],"agent.":[169],"Future":[170],"work":[171],"will":[172],"focus":[173],"extending":[175],"framework":[179],"multi-device":[181],"multi-edge":[183],"environments.":[184]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-14T00:00:00"}