{"id":"https://openalex.org/W4406258462","doi":"https://doi.org/10.1109/tsusc.2025.3528105","title":"Serving Transformer Models via Joint Requst Scheduling and Batching in the Network Edge","display_name":"Serving Transformer Models via Joint Requst Scheduling and Batching in the Network Edge","publication_year":2025,"publication_date":"2025-01-10","ids":{"openalex":"https://openalex.org/W4406258462","doi":"https://doi.org/10.1109/tsusc.2025.3528105"},"language":"en","primary_location":{"id":"doi:10.1109/tsusc.2025.3528105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsusc.2025.3528105","pdf_url":null,"source":{"id":"https://openalex.org/S4210221417","display_name":"IEEE Transactions on Sustainable Computing","issn_l":"2377-3782","issn":["2377-3782","2377-3790"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Sustainable Computing","raw_type":"journal-article"},"type":"article","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/A5027046756","display_name":"Boqian Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Boqian Fu","raw_affiliation_strings":["School of Computer Science and Engineering, University of Aizu, Aizuwakamatsu, Japan","School of Computer Science and Engineering, University of Aizu, Japan"],"raw_orcid":"https://orcid.org/0009-0000-2824-7927","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Aizu, Aizuwakamatsu, Japan","institution_ids":["https://openalex.org/I141591182"]},{"raw_affiliation_string":"School of Computer Science and Engineering, University of Aizu, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088461411","display_name":"Fahao Chen","orcid":"https://orcid.org/0000-0002-4345-1296"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Fahao Chen","raw_affiliation_strings":["School of Computer Science and Engineering, University of Aizu, Aizuwakamatsu, Japan","School of Computer Science and Engineering, University of Aizu, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Aizu, Aizuwakamatsu, Japan","institution_ids":["https://openalex.org/I141591182"]},{"raw_affiliation_string":"School of Computer Science and Engineering, University of Aizu, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066098631","display_name":"Peng Li","orcid":"https://orcid.org/0000-0002-5303-0700"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Li","raw_affiliation_strings":["School of Cyber Science and Engineering, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China","School of Cyber Science and Engineering, Xi&#x0027;an Jiaotong University, China"],"raw_orcid":"https://orcid.org/0000-0002-5303-0700","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Cyber Science and Engineering, Xi&#x0027;an Jiaotong University, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077093242","display_name":"Deze Zeng","orcid":"https://orcid.org/0000-0003-3276-1202"},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deze Zeng","raw_affiliation_strings":["School of Computer Science, China University of Geosciences, Wuhan, China","School of Computer Science, China University of Geosciences ( Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-3276-1202","affiliations":[{"raw_affiliation_string":"School of Computer Science, China University of Geosciences, Wuhan, China","institution_ids":["https://openalex.org/I3124059619"]},{"raw_affiliation_string":"School of Computer Science, China University of Geosciences ( Wuhan, China","institution_ids":["https://openalex.org/I3124059619"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.792,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89563412,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"10","issue":"4","first_page":"678","last_page":"689"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9847000241279602,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7203486561775208},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7061631083488464},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5721336603164673},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5542857646942139},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.37187033891677856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3446806073188782},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1293899416923523}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7203486561775208},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7061631083488464},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5721336603164673},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5542857646942139},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37187033891677856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3446806073188782},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1293899416923523},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsusc.2025.3528105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsusc.2025.3528105","pdf_url":null,"source":{"id":"https://openalex.org/S4210221417","display_name":"IEEE Transactions on Sustainable Computing","issn_l":"2377-3782","issn":["2377-3782","2377-3790"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Sustainable Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4040622270","display_name":"Time-Evolving Graph Learning with Algorithm-System Co-Design","funder_award_id":"23KJ1786","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7935549449","display_name":null,"funder_award_id":"62471383","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2144578941","https://openalex.org/W2251939518","https://openalex.org/W2923014074","https://openalex.org/W2964199361","https://openalex.org/W3005664618","https://openalex.org/W3016939927","https://openalex.org/W3035016936","https://openalex.org/W3047371394","https://openalex.org/W3130716829","https://openalex.org/W3158444059","https://openalex.org/W3165292244","https://openalex.org/W3169109617","https://openalex.org/W3189877953","https://openalex.org/W3211336323","https://openalex.org/W3211525823","https://openalex.org/W4212986322","https://openalex.org/W4320067926","https://openalex.org/W4385245566","https://openalex.org/W4386707601","https://openalex.org/W6713134421","https://openalex.org/W6730956707","https://openalex.org/W6755207826","https://openalex.org/W6766978945","https://openalex.org/W6769627184","https://openalex.org/W6778883912","https://openalex.org/W6780069040","https://openalex.org/W6785051108","https://openalex.org/W6785377559","https://openalex.org/W6790665546","https://openalex.org/W6795121908","https://openalex.org/W6799372109"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W1986418932","https://openalex.org/W2357796999","https://openalex.org/W4321636575","https://openalex.org/W2741131631","https://openalex.org/W2045526782","https://openalex.org/W4206178588","https://openalex.org/W3094491777","https://openalex.org/W3214715529","https://openalex.org/W4287635093"],"abstract_inverted_index":{"Transformers":[0],"have":[1],"dominated":[2],"the":[3,32,50,71,127],"field":[4],"of":[5,22,35,42,52,129,156],"natural":[6],"language":[7],"processing,":[8],"attributed":[9],"to":[10,13,108,125,147],"their":[11],"capability":[12],"handle":[14],"sequential":[15],"input":[16],"data.":[17],"There":[18],"is":[19],"a":[20,40,92,101,133,139],"surge":[21],"work":[23],"on":[24,66,151],"computational":[25,62,110],"and":[26,76,143],"networking":[27],"optimizations,":[28],"aimed":[29],"at":[30],"improving":[31],"training":[33],"efficiency":[34],"Transformers.":[36],"However,":[37],"transformer":[38,67],"inference,":[39],"cornerstone":[41],"myriad":[43],"AI":[44],"services,":[45],"remains":[46],"relatively":[47],"underexplored.":[48],"With":[49],"challenge":[51],"variable-length":[53],"inputs,":[54],"conventional":[55],"methods":[56,164],"adopt":[57],"padding":[58],"schemes,":[59],"resulting":[60],"in":[61,82],"waste.":[63],"Moreover,":[64],"works":[65],"inference":[68,83,97],"often":[69],"overlook":[70],"integration":[72],"between":[73],"request":[74,121,141],"scheduling":[75,145],"batching,":[77],"which":[78],"play":[79],"pivotal":[80],"roles":[81],"systems.":[84],"To":[85],"address":[86],"these":[87],"challenges,":[88],"we":[89,117,136],"introduce":[90,138],"TCB,":[91],"comprehensive":[93],"<bold":[94,102],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[95,103,105],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">T</b>ransformer":[96],"system":[98],"that":[99,161],"integrates":[100],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">C</b>oncat<bold":[104],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">B</b>atching":[106],"scheme":[107],"reduce":[109],"redundancy":[111],"by":[112],"concatenating":[113],"requests.":[114,131],"In":[115],"addition,":[116],"present":[118],"an":[119],"online":[120],"batching":[122,144],"algorithm,":[123],"designed":[124],"augment":[126],"throughput":[128],"scheduled":[130],"Consider":[132],"muiti-server":[134],"case,":[135],"further":[137],"joint":[140],"assignment":[142],"policy":[146],"fully":[148],"utilize":[149],"resources":[150],"servers":[152],"while":[153],"ensuring":[154],"quality-of-service":[155],"inference.":[157],"Extensive":[158],"experiments":[159],"demonstrate":[160],"our":[162],"proposed":[163],"can":[165],"significantly":[166],"outperform":[167],"existing":[168],"works.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}