{"id":"https://openalex.org/W3163768429","doi":"https://doi.org/10.1109/tpds.2021.3081600","title":"GML: Efficiently Auto-Tuning Flink's Configurations Via Guided Machine Learning","display_name":"GML: Efficiently Auto-Tuning Flink's Configurations Via Guided Machine Learning","publication_year":2021,"publication_date":"2021-05-18","ids":{"openalex":"https://openalex.org/W3163768429","doi":"https://doi.org/10.1109/tpds.2021.3081600","mag":"3163768429"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2021.3081600","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3081600","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","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/A5015794055","display_name":"Yijin Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yijin Guo","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Science (CAS), Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Science (CAS), Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028129292","display_name":"Huasong Shan","orcid":"https://orcid.org/0000-0001-7268-8439"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huasong Shan","raw_affiliation_strings":["JD.com American Technologies Corporation, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-7268-8439","affiliations":[{"raw_affiliation_string":"JD.com American Technologies Corporation, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064311448","display_name":"Shixin Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shixin Huang","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Science (CAS), Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Science (CAS), Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103001853","display_name":"Kai Hwang","orcid":"https://orcid.org/0000-0003-2673-4953"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Hwang","raw_affiliation_strings":["Computer Science and Engineering, Chinese University of Hong Kong (CUHK), Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Chinese University of Hong Kong (CUHK), Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100728566","display_name":"Jianping Fan","orcid":"https://orcid.org/0000-0002-7389-9112"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianping Fan","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Science (CAS), Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Science (CAS), Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048614443","display_name":"Zhibin Yu","orcid":"https://orcid.org/0000-0001-8067-9612"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhibin Yu","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Science (CAS), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-8067-9612","affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Science (CAS), Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5015794055"],"corresponding_institution_ids":["https://openalex.org/I4210145761"],"apc_list":null,"apc_paid":null,"fwci":5.688,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.96024715,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"32","issue":"12","first_page":"2921","last_page":"2935"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9983000159263611,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9983000159263611,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9977999925613403,"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/T11891","display_name":"Big Data and Business Intelligence","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8663922548294067},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7614938020706177},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6499751210212708},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5737534761428833},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.49036622047424316},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4815921485424042},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46349120140075684},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42268800735473633},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3036487102508545},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15532302856445312}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8663922548294067},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7614938020706177},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6499751210212708},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5737534761428833},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.49036622047424316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4815921485424042},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46349120140075684},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42268800735473633},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3036487102508545},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15532302856445312},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2021.3081600","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3081600","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G5903059524","display_name":null,"funder_award_id":"61672511","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6139807279","display_name":null,"funder_award_id":"61802384","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6385625218","display_name":null,"funder_award_id":"61702495","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/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W136979389","https://openalex.org/W1794174336","https://openalex.org/W1834532152","https://openalex.org/W1972281688","https://openalex.org/W2011973765","https://openalex.org/W2017855273","https://openalex.org/W2091422786","https://openalex.org/W2099471712","https://openalex.org/W2117358165","https://openalex.org/W2148736953","https://openalex.org/W2157490430","https://openalex.org/W2191029871","https://openalex.org/W2247317079","https://openalex.org/W2251801071","https://openalex.org/W2294316975","https://openalex.org/W2318383848","https://openalex.org/W2486439025","https://openalex.org/W2561824179","https://openalex.org/W2566979091","https://openalex.org/W2589755300","https://openalex.org/W2623708532","https://openalex.org/W2745879824","https://openalex.org/W2752764103","https://openalex.org/W2792529086","https://openalex.org/W2977337932","https://openalex.org/W2999515616","https://openalex.org/W3012532133","https://openalex.org/W3022630129","https://openalex.org/W3102059167","https://openalex.org/W4297814130","https://openalex.org/W4298018943","https://openalex.org/W4320013936","https://openalex.org/W6638329389","https://openalex.org/W6639007902","https://openalex.org/W6731596640"],"related_works":["https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W3202731209","https://openalex.org/W4240326769","https://openalex.org/W3211874991","https://openalex.org/W3012518171","https://openalex.org/W2906268655","https://openalex.org/W4241605045"],"abstract_inverted_index":{"The":[0,167],"increasingly":[1],"popular":[2],"fused":[3],"batch-streaming":[4],"big":[5,44],"data":[6,45,67,94,124,193],"framework,":[7],"Apache":[8,48],"Flink,":[9],"has":[10,27,35],"many":[11],"performance-critical":[12],"as":[13,15],"well":[14],"untamed":[16],"configuration":[17],"parameters.":[18],"However,":[19,54],"how":[20],"to":[21,38,60,81,96,111,132,218,221],"tune":[22,39,82],"them":[23],"for":[24,42,91,122,183],"optimal":[25],"performance":[26,52,138,144],"not":[28],"yet":[29],"been":[30,36],"explored.":[31],"Machine":[32],"learning":[33,78],"(ML)":[34],"chosen":[37],"the":[40,83,119,136,142,174,185,209,214,222,226],"configurations":[41,84,134,186,223],"other":[43],"frameworks":[46],"(e.g.,":[47],"Spark),":[49],"showing":[50],"significant":[51],"improvements.":[53],"it":[55,105,212],"needs":[56],"a":[57,62,75,113,129,152,159],"long":[58],"time":[59,90,120,195],"collect":[61],"large":[63],"amount":[64],"of":[65,85,115,145,187,191],"training":[66,93,116,123],"by":[68,216,225],"nature.":[69],"In":[70],"this":[71],"article,":[72],"we":[73],"propose":[74],"guided":[76],"machine":[77],"(GML)":[79],"approach":[80],"Flink":[86],"with":[87,155,189,197],"significantly":[88,172],"shorter":[89],"collecting":[92],"compared":[95,220],"traditional":[97],"ML":[98,130],"approaches.":[99],"GML":[100,127,150,171,205],"innovates":[101],"two":[102],"techniques.":[103],"First,":[104],"leverages":[106],"generative":[107],"adversarial":[108],"networks":[109],"(GANs)":[110],"generate":[112],"part":[114],"data,":[117],"reducing":[118],"needed":[121],"collection.":[125],"Second,":[126],"guides":[128],"algorithm":[131],"select":[133],"that":[135,170],"corresponding":[137],"is":[139,206],"higher":[140],"than":[141],"average":[143],"random":[146],"configurations.":[147],"We":[148],"evaluate":[149],"on":[151],"lab":[153],"cluster":[154,162],"4":[156],"servers":[157],"and":[158],"real":[160],"production":[161],"in":[163,208],"an":[164],"internet":[165,210],"company.":[166,227],"results":[168],"show":[169],"outperforms":[173],"state-of-the-art,":[175],"DAC":[176],"(Datasize-Aware-Configuration)":[177],"(Z.":[178],"Yu":[179],"et":[180],"al.":[181],"2018)":[182],"tuning":[184],"Spark,":[188],"2.4\u00d7":[190],"reduced":[192,200],"collection":[194],"but":[196],"30":[198],"percent":[199],"99th":[201],"percentile":[202],"latency.":[203],"When":[204],"used":[207],"company,":[211],"reduces":[213],"latency":[215],"up":[217],"57.8\u00d7":[219],"made":[224]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-09T13:55:54.758798","created_date":"2025-10-10T00:00:00"}