{"id":"https://openalex.org/W4414169712","doi":"https://doi.org/10.1109/iwqos65803.2025.11143263","title":"Diffusion-Type AIGC Request Scheduling with Inference Sharing","display_name":"Diffusion-Type AIGC Request Scheduling with Inference Sharing","publication_year":2025,"publication_date":"2025-07-02","ids":{"openalex":"https://openalex.org/W4414169712","doi":"https://doi.org/10.1109/iwqos65803.2025.11143263"},"language":"en","primary_location":{"id":"doi:10.1109/iwqos65803.2025.11143263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos65803.2025.11143263","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM 33rd International Symposium on Quality of Service (IWQoS)","raw_type":"proceedings-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/A5113964750","display_name":"Han Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Han Yang","raw_affiliation_strings":["Institute for Network Sciences and Cyberspace, Tsinghua University,China"],"affiliations":[{"raw_affiliation_string":"Institute for Network Sciences and Cyberspace, Tsinghua University,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069824236","display_name":"Yeqiao Hou","orcid":"https://orcid.org/0009-0000-8195-1059"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yeqiao Hou","raw_affiliation_strings":["Quan Cheng Laboratory,China"],"affiliations":[{"raw_affiliation_string":"Quan Cheng Laboratory,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101489016","display_name":"Ying Zheng","orcid":"https://orcid.org/0000-0001-8823-2460"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Zheng","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Fudan University,China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Fudan University,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066247159","display_name":"Zongpeng Li","orcid":"https://orcid.org/0000-0001-5351-2075"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongpeng Li","raw_affiliation_strings":["Institute for Network Sciences and Cyberspace, Tsinghua University,China"],"affiliations":[{"raw_affiliation_string":"Institute for Network Sciences and Cyberspace, Tsinghua University,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113964750"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2967288,"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":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9815000295639038,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9815000295639038,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11165","display_name":"Image and Video Quality Assessment","score":0.9659000039100647,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.954800009727478,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/inference","display_name":"Inference","score":0.620199978351593},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6003999710083008},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.44130000472068787},{"id":"https://openalex.org/keywords/service-provider","display_name":"Service provider","score":0.4049000144004822},{"id":"https://openalex.org/keywords/shared-resource","display_name":"Shared resource","score":0.3637000024318695},{"id":"https://openalex.org/keywords/service-quality","display_name":"Service quality","score":0.3107999861240387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8259999752044678},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.620199978351593},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6003999710083008},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5121999979019165},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.44130000472068787},{"id":"https://openalex.org/C116537","wikidata":"https://www.wikidata.org/wiki/Q2169973","display_name":"Service provider","level":3,"score":0.4049000144004822},{"id":"https://openalex.org/C51332947","wikidata":"https://www.wikidata.org/wiki/Q1172305","display_name":"Shared resource","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C140781008","wikidata":"https://www.wikidata.org/wiki/Q1221081","display_name":"Service quality","level":3,"score":0.3107999861240387},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.31049999594688416},{"id":"https://openalex.org/C31689143","wikidata":"https://www.wikidata.org/wiki/Q733809","display_name":"Fair-share scheduling","level":3,"score":0.289900004863739},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.28790000081062317},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.27090001106262207},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.2590000033378601}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwqos65803.2025.11143263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos65803.2025.11143263","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM 33rd International Symposium on Quality of Service (IWQoS)","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":21,"referenced_works":["https://openalex.org/W1982471090","https://openalex.org/W2123035833","https://openalex.org/W2527855297","https://openalex.org/W2946772172","https://openalex.org/W3153469116","https://openalex.org/W3162926177","https://openalex.org/W3186875089","https://openalex.org/W4236587599","https://openalex.org/W4283219267","https://openalex.org/W4312497550","https://openalex.org/W4366457968","https://openalex.org/W4382462760","https://openalex.org/W4382998652","https://openalex.org/W4386260505","https://openalex.org/W4391019625","https://openalex.org/W4392341509","https://openalex.org/W4401541341","https://openalex.org/W4402897399","https://openalex.org/W4402981529","https://openalex.org/W4405488026","https://openalex.org/W4406356998"],"related_works":[],"abstract_inverted_index":{"AIGC-as-a-Service":[0],"(AaaS)":[1],"enables":[2],"diverse":[3],"and":[4,13,40,48,62,107,151],"high-quality":[5],"content":[6],"creation.":[7],"Due":[8],"to":[9,64,124,146,177,180],"the":[10,56,66,103,109,126,157,181],"computational":[11],"intensity":[12],"high":[14],"costs":[15],"of":[16,59,128,156],"model":[17,70,101],"inference,":[18],"efficiently":[19],"scheduling":[20,52,110],"generation":[21,36,162],"requests":[22],"is":[23,33],"non-trivial":[24],"for":[25],"AIGC":[26,158],"Service":[27],"Providers":[28],"(ASPs).":[29],"A":[30],"judicious":[31],"balance":[32],"required":[34],"between":[35],"quality,":[37],"limited":[38],"resources,":[39],"service":[41],"delay,":[42],"while":[43,160],"coping":[44],"with":[45],"online":[46,144],"arrivals":[47],"operational":[49],"constraints.":[50],"Existing":[51],"systems":[53],"often":[54],"neglect":[55],"quality":[57,100],"metrics":[58],"generated":[60],"content,":[61],"fail":[63],"deploy":[65],"latest":[67],"architecture":[68],"in":[69],"inference.":[71],"To":[72],"address":[73],"these":[74],"challenges,":[75],"we":[76,97,140],"introduce":[77],"a":[78,99,113,120,137],"distributed":[79],"diffusion":[80],"framework":[81],"that":[82,169],"reduces":[83],"resource":[84],"consumption":[85],"by":[86,175],"sharing":[87],"inference":[88,92,130],"steps":[89,131],"across":[90],"different":[91],"tasks.":[93],"On":[94],"this":[95],"basis,":[96],"establish":[98],"using":[102],"refined":[104],"CLIP":[105],"Score,":[106],"formulate":[108],"problem":[111],"as":[112],"mixed-integer":[114],"nonlinear":[115],"program.":[116],"We":[117],"first":[118],"develop":[119],"prompt":[121],"similarity-based":[122],"algorithm":[123,145],"determine":[125],"number":[127],"shared":[129],"within":[132],"each":[133],"request":[134,149],"group.":[135],"Adopting":[136],"primal-dual":[138],"framework,":[139],"then":[141],"design":[142],"an":[143],"dynamically":[147],"manage":[148],"admission":[150],"scheduling,":[152],"maximizing":[153],"social":[154,173],"welfare":[155,174],"ecosystem":[159],"ensuring":[161],"quality.":[163],"Extensive":[164],"real-world":[165],"trace-driven":[166],"experiments":[167],"demonstrate":[168],"our":[170],"approach":[171],"improves":[172],"up":[176],"38.2%":[178],"compared":[179],"state-of-the-art":[182],"method.":[183]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}