{"id":"https://openalex.org/W4283837702","doi":"https://doi.org/10.1109/iwqos54832.2022.9812905","title":"AIQoSer: Building the efficient Inference-QoS for AI Services","display_name":"AIQoSer: Building the efficient Inference-QoS for AI Services","publication_year":2022,"publication_date":"2022-06-10","ids":{"openalex":"https://openalex.org/W4283837702","doi":"https://doi.org/10.1109/iwqos54832.2022.9812905"},"language":"en","primary_location":{"id":"doi:10.1109/iwqos54832.2022.9812905","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos54832.2022.9812905","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/ACM 30th 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/A5100380469","display_name":"Jianxin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianxin Li","raw_affiliation_strings":["Beihang University,Advanced Innovation Center for Big Data and Brain Computing,Beijing,China,100191","School of Computer Science and Engineering, Beihang University, Beijing, China","State Key Laboratory of Software Development Environment, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University,Advanced Innovation Center for Big Data and Brain Computing,Beijing,China,100191","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"State Key Laboratory of Software Development Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024079569","display_name":"Tianchen Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianchen Zhu","raw_affiliation_strings":["Beihang University,Advanced Innovation Center for Big Data and Brain Computing,Beijing,China,100191","Shenyuan Honors College, Beihang University, Beijing, China","School of Computer Science and Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University,Advanced Innovation Center for Big Data and Brain Computing,Beijing,China,100191","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Shenyuan Honors College, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086419494","display_name":"Haoyi Zhou","orcid":"https://orcid.org/0000-0002-2393-3634"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyi Zhou","raw_affiliation_strings":["Beihang University,Advanced Innovation Center for Big Data and Brain Computing,Beijing,China,100191","School of Software, Beihang University, Beijing, China","State Key Laboratory of Software Development Environment, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University,Advanced Innovation Center for Big Data and Brain Computing,Beijing,China,100191","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Software, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"State Key Laboratory of Software Development Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018132697","display_name":"Qingyun Sun","orcid":"https://orcid.org/0000-0003-1930-3848"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyun Sun","raw_affiliation_strings":["Beihang University,Advanced Innovation Center for Big Data and Brain Computing,Beijing,China,100191","School of Computer Science and Engineering, Beihang University, Beijing, China","Shenyuan Honors College, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University,Advanced Innovation Center for Big Data and Brain Computing,Beijing,China,100191","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Shenyuan Honors College, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000483812","display_name":"Chunyang Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunyang Jiang","raw_affiliation_strings":["Beihang University,Advanced Innovation Center for Big Data and Brain Computing,Beijing,China,100191","School of Computer Science and Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University,Advanced Innovation Center for Big Data and Brain Computing,Beijing,China,100191","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328838","display_name":"Shuai Zhang","orcid":"https://orcid.org/0000-0001-8502-2927"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Zhang","raw_affiliation_strings":["Beihang University,Advanced Innovation Center for Big Data and Brain Computing,Beijing,China,100191","School of Computer Science and Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University,Advanced Innovation Center for Big Data and Brain Computing,Beijing,China,100191","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086470621","display_name":"Chunming Hu","orcid":"https://orcid.org/0000-0002-9502-3955"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunming Hu","raw_affiliation_strings":["Beihang University,Advanced Innovation Center for Big Data and Brain Computing,Beijing,China,100191","School of Software, Beihang University, Beijing, China","State Key Laboratory of Software Development Environment, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University,Advanced Innovation Center for Big Data and Brain Computing,Beijing,China,100191","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Software, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"State Key Laboratory of Software Development Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100380469"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.4234,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.57768665,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/T10241","display_name":"Functional Brain Connectivity Studies","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9843999743461609,"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/inference","display_name":"Inference","score":0.8282842636108398},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7731764316558838},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.7111547589302063},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5627655982971191},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5571566820144653},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5325704216957092},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.48658645153045654},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4860594570636749},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.4857052266597748},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3906075060367584},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36427783966064453},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2869337201118469},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08591046929359436}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8282842636108398},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7731764316558838},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.7111547589302063},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5627655982971191},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5571566820144653},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5325704216957092},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.48658645153045654},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4860594570636749},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.4857052266597748},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3906075060367584},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36427783966064453},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2869337201118469},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08591046929359436},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwqos54832.2022.9812905","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos54832.2022.9812905","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/ACM 30th International Symposium on Quality of Service (IWQoS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W1841592590","https://openalex.org/W1924770834","https://openalex.org/W2064675550","https://openalex.org/W2116788941","https://openalex.org/W2125389748","https://openalex.org/W2145563843","https://openalex.org/W2285660444","https://openalex.org/W2319920447","https://openalex.org/W2592335154","https://openalex.org/W2617931713","https://openalex.org/W2768254111","https://openalex.org/W2782912001","https://openalex.org/W2792764867","https://openalex.org/W2803113791","https://openalex.org/W2858629302","https://openalex.org/W2886851211","https://openalex.org/W2894393199","https://openalex.org/W2896409484","https://openalex.org/W2903475457","https://openalex.org/W2908510526","https://openalex.org/W2950248853","https://openalex.org/W2954731415","https://openalex.org/W2963432161","https://openalex.org/W2963542740","https://openalex.org/W2963631907","https://openalex.org/W3003635954","https://openalex.org/W3087130277","https://openalex.org/W3091858314","https://openalex.org/W3094502228","https://openalex.org/W3137147200","https://openalex.org/W3177318507","https://openalex.org/W3183673024","https://openalex.org/W3213170289","https://openalex.org/W3215152557","https://openalex.org/W4239560345","https://openalex.org/W4287363917","https://openalex.org/W4385245566","https://openalex.org/W6638523607","https://openalex.org/W6638783484","https://openalex.org/W6640212811","https://openalex.org/W6678583879","https://openalex.org/W6684563725","https://openalex.org/W6700264148","https://openalex.org/W6739901393","https://openalex.org/W6745220581","https://openalex.org/W6749825310","https://openalex.org/W6751528251","https://openalex.org/W6753065222","https://openalex.org/W6754905691","https://openalex.org/W6755843862","https://openalex.org/W6757817989","https://openalex.org/W6764679822","https://openalex.org/W6784333009","https://openalex.org/W6790503700","https://openalex.org/W6791940793"],"related_works":["https://openalex.org/W4361804730","https://openalex.org/W2142113611","https://openalex.org/W2334467465","https://openalex.org/W2087870008","https://openalex.org/W2162534555","https://openalex.org/W2752178021","https://openalex.org/W2107419853","https://openalex.org/W2143024819","https://openalex.org/W4247159817","https://openalex.org/W2964201926"],"abstract_inverted_index":{"The":[0],"AI":[1,28,66,106],"inspired":[2],"methods":[3],"have":[4],"entirely":[5],"changed":[6],"the":[7,17,20,34,38,50,55,76,97,101,130],"network":[8,40,56],"QoS":[9,57,78],"landscape":[10],"and":[11,63,87,138,153],"brought":[12],"better":[13],"demand-guided":[14],"experiences":[15,25],"for":[16,65,99,141],"end-users.":[18],"However,":[19],"increasing":[21],"demands":[22],"of":[23,54,136],"satisfactory":[24],"require":[26],"larger":[27],"models,":[29],"whose":[30],"inference":[31,61,85,124,151],"efficiency":[32,62],"becomes":[33],"non-negligible":[35],"drawback":[36],"in":[37,104,134],"time-sensitive":[39],"QoS.":[41],"In":[42],"this":[43,47],"work,":[44],"we":[45,91],"defined":[46],"challenge":[48],"as":[49,96],"inference-QoS":[51],"(iQoS)":[52],"problem":[53],"itself,":[58],"which":[59],"balances":[60],"performance":[64],"services.":[67],"We":[68],"design":[69],"a":[70,93],"unified":[71],"iQoS":[72,102],"metric":[73,103],"to":[74],"evaluate":[75],"AI-enhanced":[77],"frameworks":[79],"with":[80],"considerations":[81],"on":[82,145],"model":[83],"performance,":[84],"latency,":[86],"input":[88],"scale.":[89],"Then,":[90],"propose":[92],"two-stage":[94],"pipeline":[95],"exemplar":[98],"leveraging":[100],"QoS-aware":[105],"services:":[107],"(i)":[108],"enhance":[109],"reconstruction":[110],"ability,":[111],"pretraining":[112],"masked":[113,127],"autoencoder":[114],"extracts":[115],"intrinsic":[116],"data":[117,131],"correlations":[118],"by":[119],"multi-scale":[120],"masking;":[121],"(ii)":[122],"improve":[123],"efficiency,":[125],"forecasting":[126],"decoder":[128],"uses":[129],"scale":[132],"pruning":[133],"terms":[135],"spatial":[137],"temporal":[139],"dimension":[140],"prediction.":[142],"Comprehensive":[143],"experiments":[144],"our":[146],"method":[147],"demonstrate":[148],"its":[149],"superior":[150],"latency":[152],"overwhelming":[154],"traffic":[155],"matrix":[156],"prediction":[157],"performance.":[158]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}