{"id":"https://openalex.org/W3169109617","doi":"https://doi.org/10.1145/3447548.3467146","title":"JIZHI: A Fast and Cost-Effective Model-As-A-Service System for Web-Scale Online Inference at Baidu","display_name":"JIZHI: A Fast and Cost-Effective Model-As-A-Service System for Web-Scale Online Inference at Baidu","publication_year":2021,"publication_date":"2021-08-12","ids":{"openalex":"https://openalex.org/W3169109617","doi":"https://doi.org/10.1145/3447548.3467146","mag":"3169109617"},"language":"en","primary_location":{"id":"doi:10.1145/3447548.3467146","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3467146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","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/A5100458867","display_name":"Hao Liu","orcid":"https://orcid.org/0000-0003-0510-6501"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Liu","raw_affiliation_strings":["Baidu, Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu, Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021552476","display_name":"Qian Gao","orcid":"https://orcid.org/0000-0002-0239-8708"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Gao","raw_affiliation_strings":["Baidu, Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu, Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392353","display_name":"Li Jiang","orcid":"https://orcid.org/0000-0001-7058-6957"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang Li","raw_affiliation_strings":["Baidu, Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu, Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044128348","display_name":"Xiaochao Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaochao Liao","raw_affiliation_strings":["Baidu, Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu, Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036990432","display_name":"Hao Xiong","orcid":"https://orcid.org/0000-0001-7144-2621"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Xiong","raw_affiliation_strings":["Baidu, Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu, Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101120575","display_name":"Guangxing Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangxing Chen","raw_affiliation_strings":["Baidu, Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu, Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101558665","display_name":"Wenlin Wang","orcid":"https://orcid.org/0000-0003-0838-1920"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenlin Wang","raw_affiliation_strings":["Baidu, Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu, Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039683708","display_name":"Guobao Yang","orcid":"https://orcid.org/0009-0003-1685-8327"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guobao Yang","raw_affiliation_strings":["Baidu, Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu, Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056837500","display_name":"Zhiwei Zha","orcid":"https://orcid.org/0009-0002-7005-0372"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Zha","raw_affiliation_strings":["Baidu, Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu, Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027969886","display_name":"Daxiang Dong","orcid":"https://orcid.org/0000-0003-4639-3375"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daxiang Dong","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021332177","display_name":"Dejing Dou","orcid":"https://orcid.org/0000-0003-2949-6874"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dejing Dou","raw_affiliation_strings":["Baidu, Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu, Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081254155","display_name":"Haoyi Xiong","orcid":"https://orcid.org/0000-0002-5451-3253"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyi Xiong","raw_affiliation_strings":["Baidu, Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu, Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5100458867"],"corresponding_institution_ids":["https://openalex.org/I98301712"],"apc_list":null,"apc_paid":null,"fwci":2.7507,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.90481179,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3289","last_page":"3298"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9990000128746033,"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/T11478","display_name":"Caching and Content Delivery","score":0.9990000128746033,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9951000213623047,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8263575434684753},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6205825209617615},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5926011800765991},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5143688917160034},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4659963846206665},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.452923446893692},{"id":"https://openalex.org/keywords/inference-engine","display_name":"Inference engine","score":0.4391215145587921},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.4260643422603607},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.40864086151123047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35889315605163574},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34967780113220215},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2769731283187866},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.26548752188682556},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12115773558616638}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8263575434684753},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6205825209617615},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5926011800765991},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5143688917160034},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4659963846206665},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.452923446893692},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.4391215145587921},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.4260643422603607},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.40864086151123047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35889315605163574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34967780113220215},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2769731283187866},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.26548752188682556},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12115773558616638},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3447548.3467146","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3467146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W157921099","https://openalex.org/W1993882792","https://openalex.org/W2039189705","https://openalex.org/W2048266589","https://openalex.org/W2052207834","https://openalex.org/W2057819258","https://openalex.org/W2087402357","https://openalex.org/W2474119684","https://openalex.org/W2605350416","https://openalex.org/W2606722458","https://openalex.org/W2723293840","https://openalex.org/W2883929540","https://openalex.org/W2950616914","https://openalex.org/W2950960796","https://openalex.org/W2951045934","https://openalex.org/W2951641587","https://openalex.org/W2953198391","https://openalex.org/W2963640793","https://openalex.org/W2963842088","https://openalex.org/W2976670629","https://openalex.org/W2984020950","https://openalex.org/W3011595896","https://openalex.org/W3015302520","https://openalex.org/W3080795190","https://openalex.org/W3093977741","https://openalex.org/W3150739942","https://openalex.org/W4250981202"],"related_works":["https://openalex.org/W2968745142","https://openalex.org/W2809363009","https://openalex.org/W2348159088","https://openalex.org/W2045871438","https://openalex.org/W2499363748","https://openalex.org/W77608668","https://openalex.org/W2298102683","https://openalex.org/W3200382295","https://openalex.org/W4386243286","https://openalex.org/W3206621799"],"abstract_inverted_index":{"In":[0,61,103],"modern":[1],"internet":[2],"industries,":[3],"deep":[4,39,85],"learning":[5],"based":[6],"recommender":[7],"systems":[8],"have":[9,226],"became":[10],"an":[11,187],"indispensable":[12],"building":[13],"block":[14],"for":[15,41,94],"a":[16,58,68,115,128,150],"wide":[17],"spectrum":[18],"of":[19,55,77,79,91,108,138,198,233,238],"applications,":[20],"such":[21],"as":[22],"search":[23],"engine,":[24],"news":[25],"feed,":[26],"and":[27,154,162,176,214,244,265],"short":[28],"video":[29],"clips.":[30],"However,":[31],"it":[32],"remains":[33],"challenging":[34],"to":[35,48,83,114,127,165,194,229],"carry":[36],"the":[37,49,105,124,160,168,196,201,206,216,231,236,277],"well-trained":[38],"models":[40,86],"online":[42,80,169],"real-time":[43,97,139],"inference":[44,81,106,140,170,278],"serving,":[45],"with":[46,87],"respect":[47],"time-varying":[50],"web-scale":[51],"traffics":[52,137,274],"from":[53,211,235],"billions":[54],"users,":[56],"in":[57,123,149,249,263],"cost-effective":[59],"manner.":[60],"this":[62],"work,":[63],"we":[64],"present":[65],"JIZHI":[66,158,199,234,252],"-":[67,71],"Model-as-a-Service":[69],"system":[70,222],"that":[72],"per":[73,268],"second":[74],"handles":[75],"hundreds":[76],"millions":[78],"requests":[82,141],"huge":[84],"more":[88,257,273],"than":[89,258],"trillions":[90],"sparse":[92],"parameters,":[93],"over":[95,200,220],"twenty":[96],"recommendation":[98,110],"services":[99],"at":[100],"Baidu,":[101],"Inc.":[102],"JIZHI,":[104],"workflow":[107],"every":[109],"request":[111],"is":[112],"transformed":[113],"Staged":[116],"Event-Driven":[117],"Pipeline":[118],"(SEDP),":[119],"where":[120],"each":[121,143],"node":[122],"pipeline":[125],"refers":[126],"staged":[129],"computation":[130],"or":[131],"I/O":[132],"intensive":[133],"task":[134],"processor.":[135],"With":[136],"arrived,":[142],"modularized":[144],"processor":[145],"can":[146],"be":[147],"run":[148],"fully":[151],"asynchronized":[152],"way":[153],"managed":[155],"separately.":[156],"Besides,":[157],"introduces":[159],"heterogeneous":[161],"hierarchical":[163],"storage":[164],"further":[166],"accelerate":[167],"process":[171],"by":[172,182,204],"reducing":[173],"unnecessary":[174],"computations":[175],"potential":[177],"data":[178],"access":[179],"latency":[180],"induced":[181],"ultra-sparse":[183],"model":[184],"parameters.":[185],"Moreover,":[186],"intelligent":[188],"resource":[189,208,245],"manager":[190],"has":[191,253],"been":[192,227],"deployed":[193],"maximize":[195],"throughput":[197],"shared":[202],"infrastructure":[203],"searching":[205],"optimal":[207],"allocation":[209],"plan":[210],"historical":[212],"logs":[213],"fine-tuning":[215],"load":[217],"shedding":[218],"policies":[219],"intermediate":[221],"feedback.":[223],"Extensive":[224],"experiments":[225],"done":[228],"demonstrate":[230],"advantages":[232],"perspectives":[237],"end-to-end":[239],"service":[240],"latency,":[241],"system-wide":[242],"throughput,":[243],"consumption.":[246],"Since":[247],"launched":[248],"July":[250],"2019,":[251],"helped":[254],"Baidu":[255],"saved":[256],"ten":[259],"million":[260],"US":[261],"dollars":[262],"hardware":[264],"utility":[266],"costs":[267],"year":[269],"while":[270],"handling":[271],"200%":[272],"without":[275],"sacrificing":[276],"efficiency.":[279]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}