{"id":"https://openalex.org/W4413320160","doi":"https://doi.org/10.1109/fmec65595.2025.11119384","title":"AMP4EC: Adaptive Model Partitioning Framework for Efficient Deep Learning Inference in Edge Computing Environments","display_name":"AMP4EC: Adaptive Model Partitioning Framework for Efficient Deep Learning Inference in Edge Computing Environments","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413320160","doi":"https://doi.org/10.1109/fmec65595.2025.11119384"},"language":"en","primary_location":{"id":"doi:10.1109/fmec65595.2025.11119384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fmec65595.2025.11119384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 10th International Conference on Fog and Mobile Edge Computing (FMEC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071499932","display_name":"Guilin Zhang","orcid":"https://orcid.org/0000-0002-8005-2366"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guilin Zhang","raw_affiliation_strings":["George Washington University,Department of Engineering Management and Systems Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Washington University,Department of Engineering Management and Systems Engineering,USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wulan Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wulan Guo","raw_affiliation_strings":["George Washington University,Department of Engineering Management and Systems Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Washington University,Department of Engineering Management and Systems Engineering,USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001214136","display_name":"Ziqi Tan","orcid":"https://orcid.org/0009-0001-8858-2193"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziqi Tan","raw_affiliation_strings":["George Washington University,Department of Engineering Management and Systems Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Washington University,Department of Engineering Management and Systems Engineering,USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101415568","display_name":"Hailong Jiang","orcid":"https://orcid.org/0000-0003-3246-7177"},"institutions":[{"id":"https://openalex.org/I149910238","display_name":"Kent State University","ror":"https://ror.org/049pfb863","country_code":"US","type":"education","lineage":["https://openalex.org/I149910238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hailong Jiang","raw_affiliation_strings":["Kent State University,Department of Computer Science,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kent State University,Department of Computer Science,USA","institution_ids":["https://openalex.org/I149910238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.3344,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.98871337,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"97","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9049000144004822,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9049000144004822,"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/computer-science","display_name":"Computer science","score":0.8150994777679443},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.664683997631073},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.558479368686676},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5452086329460144},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5091261267662048},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4863015115261078},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3337934613227844},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3315643072128296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8150994777679443},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.664683997631073},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.558479368686676},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5452086329460144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5091261267662048},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4863015115261078},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3337934613227844},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3315643072128296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fmec65595.2025.11119384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fmec65595.2025.11119384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 10th International Conference on Fog and Mobile Edge Computing (FMEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1991539813","https://openalex.org/W2546536770","https://openalex.org/W2604319603","https://openalex.org/W2605347906","https://openalex.org/W2896792906","https://openalex.org/W2897596343","https://openalex.org/W2950405335","https://openalex.org/W2962883027","https://openalex.org/W2963163009","https://openalex.org/W2979562621","https://openalex.org/W2980856918","https://openalex.org/W2981757716","https://openalex.org/W3009962072","https://openalex.org/W3044202831","https://openalex.org/W3048596733","https://openalex.org/W4315630622","https://openalex.org/W4317038564","https://openalex.org/W4383562519","https://openalex.org/W4391248691"],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W2055243143","https://openalex.org/W2611989081","https://openalex.org/W2731899572","https://openalex.org/W4230611425","https://openalex.org/W4324372666","https://openalex.org/W4225706866","https://openalex.org/W2914646191","https://openalex.org/W3023564924","https://openalex.org/W2942586735"],"abstract_inverted_index":{"Edge":[0],"computing":[1],"facilitates":[2],"deep":[3,30,55],"learning":[4,31,56],"in":[5,33,90,96,117,151],"resource-constrained":[6,153],"environments,":[7],"but":[8],"challenges":[9],"such":[10],"as":[11],"resource":[12,38,113],"heterogeneity":[13],"and":[14,43,75,92,124,137],"dynamic":[15,40],"constraints":[16],"persist.":[17],"This":[18],"paper":[19],"introduces":[20],"AMP4EC,":[21],"an":[22],"Adaptive":[23],"Model":[24],"Partitioning":[25],"framework":[26,103],"designed":[27],"to":[28,86,99],"optimize":[29],"inference":[32,150],"edge":[34,141],"environments":[35],"through":[36],"real-time":[37],"monitoring,":[39],"model":[41,51],"partitioning,":[42],"adaptive":[44],"task":[45,63],"scheduling.":[46],"AMP4EC":[47],"features":[48],"a":[49,62,71,76,87,93],"resource-aware":[50],"partitioner":[52],"that":[53,65],"splits":[54],"models":[57],"based":[58],"on":[59],"device":[60],"capabilities,":[61],"scheduler":[64],"ensures":[66],"efficient":[67,148],"load":[68],"balancing":[69],"using":[70],"weighted":[72],"scoring":[73],"mechanism,":[74],"Docker-based":[77],"deployment":[78],"environment":[79],"for":[80,139,147],"validation.":[81],"Experimental":[82],"results":[83,132],"show":[84],"up":[85],"78%":[88],"reduction":[89],"latency":[91],"414%":[94],"improvement":[95],"throughput":[97],"compared":[98],"baseline":[100],"methods.":[101],"The":[102],"achieves":[104],"consistent":[105],"performance":[106],"with":[107],"low":[108],"scheduling":[109],"overhead":[110],"across":[111],"varying":[112],"profiles,":[114],"demonstrating":[115],"adaptability":[116],"high-resource":[118],"(1":[119],"CPU,":[120],"1":[121],"GB":[122],"RAM)":[123],"low-resource":[125],"($0.4":[126],"\\text{CPU},":[127],"512":[128],"\\text{MB}$RAM)":[129],"scenarios.":[130],"These":[131],"highlight":[133],"AMP4EC's":[134],"scalability,":[135],"efficiency,":[136],"robustness":[138],"real-world":[140],"deployments,":[142],"addressing":[143],"the":[144],"critical":[145],"need":[146],"distributed":[149],"dynamic,":[152],"environments.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":5}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}