{"id":"https://openalex.org/W4415125190","doi":"https://doi.org/10.1109/icnp65844.2025.11192426","title":"Latency-Aware Transformer Partitioning for Heterogeneous Edge Inference","display_name":"Latency-Aware Transformer Partitioning for Heterogeneous Edge Inference","publication_year":2025,"publication_date":"2025-09-22","ids":{"openalex":"https://openalex.org/W4415125190","doi":"https://doi.org/10.1109/icnp65844.2025.11192426"},"language":"en","primary_location":{"id":"doi:10.1109/icnp65844.2025.11192426","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icnp65844.2025.11192426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 33rd International Conference on Network Protocols (ICNP)","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/A5031124981","display_name":"Xiaoyao Huang","orcid":"https://orcid.org/0000-0003-2571-1979"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoyao Huang","raw_affiliation_strings":["Cloud Computing Research Institute,China Telecom,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cloud Computing Research Institute,China Telecom,Beijing,China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031124981"],"corresponding_institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45110276,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9262999892234802,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9262999892234802,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6708999872207642},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4966000020503998},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4950999915599823},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.48420000076293945},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.43700000643730164},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.42320001125335693},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.4016999900341034},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.34360000491142273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.758899986743927},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6708999872207642},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4966000020503998},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4950999915599823},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.492000013589859},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.48420000076293945},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.43700000643730164},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.42320001125335693},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3774000108242035},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.34360000491142273},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.32089999318122864},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.3149999976158142},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3091000020503998},{"id":"https://openalex.org/C3018263672","wikidata":"https://www.wikidata.org/wiki/Q1296251","display_name":"Efficient algorithm","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2702000141143799},{"id":"https://openalex.org/C3017489831","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Running time","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.26420000195503235},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icnp65844.2025.11192426","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icnp65844.2025.11192426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 33rd International Conference on Network Protocols (ICNP)","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":9,"referenced_works":["https://openalex.org/W3204998121","https://openalex.org/W4236099117","https://openalex.org/W4385245566","https://openalex.org/W4404101447","https://openalex.org/W4408017328","https://openalex.org/W4408793796","https://openalex.org/W4409641040","https://openalex.org/W4410357217","https://openalex.org/W4413755503"],"related_works":[],"abstract_inverted_index":{"Deploying":[0],"transformer":[1,79],"models":[2],"in":[3,60],"heterogeneous":[4,96],"edge":[5,42],"environments":[6],"poses":[7],"significant":[8],"challenges":[9],"due":[10],"to":[11,29,103,135],"limited":[12],"memory,":[13],"varied":[14],"compute":[15],"capabilities,":[16],"and":[17,67,87,95,115],"asymmetric":[18],"inter-node":[19],"bandwidth.":[20],"To":[21],"enable":[22],"efficient":[23,101],"distributed":[24],"inference,":[25],"it":[26],"is":[27],"necessary":[28],"partition":[30],"the":[31,62,105],"model":[32,85],"into":[33],"segments":[34],"that":[35,82,125],"can":[36],"be":[37],"collaboratively":[38],"executed":[39],"across":[40],"multiple":[41],"nodes.":[43],"However,":[44],"previous":[45],"works":[46],"predominantly":[47],"focus":[48],"on":[49,69],"either":[50],"single-point":[51],"partitioning":[52,112],"or":[53],"static":[54],"scheduling":[55],"strategies,":[56],"which":[57],"fall":[58],"short":[59],"capturing":[61],"joint":[63],"impact":[64],"of":[65],"segmentation":[66,86],"assignment":[68],"end-to-end":[70],"latency.":[71],"In":[72],"this":[73],"work,":[74],"we":[75],"formulate":[76],"a":[77,109,116],"latency-aware":[78,110],"deployment":[80],"problem":[81],"jointly":[83],"optimizes":[84],"segment-to-node":[88],"assignment,":[89],"explicitly":[90],"accounting":[91],"for":[92],"memory":[93],"constraints":[94],"communication":[97],"costs.":[98],"We":[99],"propose":[100],"algorithms":[102],"explore":[104],"solution":[106],"space,":[107],"including":[108],"balanced":[111],"heuristic":[113],"(LaBP)":[114],"dynamic":[117],"programming-based":[118],"optimal":[119],"strategy":[120],"(DP-MCP).":[121],"Extensive":[122],"experiments":[123],"demonstrate":[124],"our":[126],"approach":[127],"consistently":[128],"achieves":[129],"significantly":[130],"lower":[131],"inference":[132],"latency":[133],"compared":[134],"existing":[136],"baselines":[137],"while":[138],"maintaining":[139],"feasibility":[140],"under":[141],"stringent":[142],"resource":[143],"constraints.":[144]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-14T00:00:00"}