{"id":"https://openalex.org/W3213171603","doi":"https://doi.org/10.1109/bigdata52589.2021.9671742","title":"Training Data Reduction for Performance Models of Data Analytics Jobs in the Cloud","display_name":"Training Data Reduction for Performance Models of Data Analytics Jobs in the Cloud","publication_year":2021,"publication_date":"2021-12-15","ids":{"openalex":"https://openalex.org/W3213171603","doi":"https://doi.org/10.1109/bigdata52589.2021.9671742","mag":"3213171603"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata52589.2021.9671742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671742","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.gla.ac.uk/view/author/66347.html>","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002540373","display_name":"Jonathan Will","orcid":"https://orcid.org/0009-0005-7834-8845"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jonathan Will","raw_affiliation_strings":["Technische Universit\u00e4t Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102240429","display_name":"Onur Arslan","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Onur Arslan","raw_affiliation_strings":["Technische Universit\u00e4t Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051029385","display_name":"Jonathan Bader","orcid":"https://orcid.org/0000-0003-0391-728X"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jonathan Bader","raw_affiliation_strings":["Technische Universit\u00e4t Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024675213","display_name":"Dominik Scheinert","orcid":"https://orcid.org/0000-0003-0763-3233"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dominik Scheinert","raw_affiliation_strings":["Technische Universit\u00e4t Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084056435","display_name":"Lauritz Thamsen","orcid":"https://orcid.org/0000-0003-3755-1503"},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]},{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lauritz Thamsen","raw_affiliation_strings":["Humboldt-Universit\u00e4t zu Berlin, Germany","Technische Universit\u00e4t Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Humboldt-Universit\u00e4t zu Berlin, Germany","institution_ids":["https://openalex.org/I39343248"]},{"raw_affiliation_string":"Technische Universit\u00e4t Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7609,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.74676525,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3141","last_page":"3146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9995999932289124,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9995999932289124,"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/T11719","display_name":"Data Quality and Management","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9857000112533569,"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/computer-science","display_name":"Computer science","score":0.7470766305923462},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.7270026803016663},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.6544837951660156},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5813390612602234},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5719727873802185},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.5172322392463684},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.5082302093505859},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43870723247528076},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.40763941407203674},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3907071352005005},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.28428465127944946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16353049874305725},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15095603466033936}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7470766305923462},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7270026803016663},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.6544837951660156},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5813390612602234},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5719727873802185},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.5172322392463684},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.5082302093505859},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43870723247528076},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.40763941407203674},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3907071352005005},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28428465127944946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16353049874305725},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15095603466033936},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/bigdata52589.2021.9671742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671742","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:268162","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/66347.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"},{"id":"pmh:oai:arXiv.org:2111.07904","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.07904","pdf_url":"https://arxiv.org/pdf/2111.07904","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:eprints.gla.ac.uk:268162","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/66347.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5099999904632568}],"awards":[{"id":"https://openalex.org/G7624340995","display_name":null,"funder_award_id":"01IS18025A","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1535431348","https://openalex.org/W2023729401","https://openalex.org/W2051267297","https://openalex.org/W2101234009","https://openalex.org/W2114896543","https://openalex.org/W2173213060","https://openalex.org/W2188333987","https://openalex.org/W2189465200","https://openalex.org/W2309679942","https://openalex.org/W2521550930","https://openalex.org/W2528415359","https://openalex.org/W2535690855","https://openalex.org/W2566979091","https://openalex.org/W2572526791","https://openalex.org/W2604856537","https://openalex.org/W2793313422","https://openalex.org/W2912213068","https://openalex.org/W2949522309","https://openalex.org/W2963642335","https://openalex.org/W2963822306","https://openalex.org/W3009370840","https://openalex.org/W3102428287","https://openalex.org/W3175470932","https://openalex.org/W3197557987","https://openalex.org/W3207844152","https://openalex.org/W3211837897","https://openalex.org/W3215201015","https://openalex.org/W3216845212","https://openalex.org/W4225472196","https://openalex.org/W4226245665","https://openalex.org/W4297798504","https://openalex.org/W6632229964","https://openalex.org/W6675354045","https://openalex.org/W6687322159","https://openalex.org/W6697698479","https://openalex.org/W6727576777","https://openalex.org/W6731596640","https://openalex.org/W6735916004","https://openalex.org/W6749468489","https://openalex.org/W6773102424","https://openalex.org/W6789743831","https://openalex.org/W6800514731","https://openalex.org/W6804070521"],"related_works":["https://openalex.org/W4226266853","https://openalex.org/W4210252074","https://openalex.org/W3092201768","https://openalex.org/W2796632413","https://openalex.org/W2740083192","https://openalex.org/W2794907032","https://openalex.org/W4255802207","https://openalex.org/W4299701476","https://openalex.org/W2904574413","https://openalex.org/W2462007151"],"abstract_inverted_index":{"Distributed":[0],"dataflow":[1,28,154],"systems":[2],"like":[3],"Apache":[4,7],"Flink":[5],"and":[6,33,128],"Spark":[8],"simplify":[9],"processing":[10],"large":[11],"amounts":[12],"of":[13,85,141,147],"data":[14,83,94,109,125,136,149,163],"on":[15,144,159],"clusters":[16],"in":[17,30,124],"a":[18,70,145,161],"data-parallel":[19],"manner.":[20],"However,":[21],"choosing":[22],"suitable":[23,71],"cluster":[24],"resources":[25],"for":[26,38,73],"distributed":[27,153],"jobs":[29],"both":[31],"type":[32],"number":[34],"is":[35,55,91],"difficult,":[36],"especially":[37],"users":[39,58],"who":[40],"do":[41],"not":[42],"have":[43,57],"access":[44],"to":[45,51,56,62,106],"previous":[46],"performance":[47,65,115],"metrics.":[48],"One":[49],"approach":[50],"overcoming":[52],"this":[53],"issue":[54],"share":[59],"runtime":[60,82,148],"metrics":[61],"train":[63],"context-aware":[64],"models":[66,87,116],"that":[67,92,121],"help":[68],"find":[69],"configuration":[72],"the":[74,93,113,139],"job":[75],"at":[76],"hand.":[77],"A":[78],"problem":[79],"when":[80],"sharing":[81],"instead":[84],"trained":[86],"or":[88],"model":[89,129],"parameters":[90],"size":[95,110],"can":[96,131],"grow":[97],"substantially":[98],"over":[99],"time.This":[100],"paper":[101],"examines":[102],"several":[103],"clustering":[104],"techniques":[105],"minimize":[107],"training":[108,130,135],"while":[111],"keeping":[112],"associated":[114],"accurate.":[117],"Our":[118],"results":[119],"indicate":[120],"efficiency":[122],"gains":[123],"transfer,":[126],"storage,":[127],"be":[132],"achieved":[133],"through":[134],"reduction.":[137],"In":[138],"evaluation":[140],"our":[142],"solution":[143],"dataset":[146],"from":[150],"930":[151],"unique":[152],"jobs,":[155],"we":[156],"observed":[157],"that,":[158],"average,":[160],"75%":[162],"reduction":[164],"only":[165],"increases":[166],"prediction":[167],"errors":[168],"by":[169],"one":[170],"percentage":[171],"point.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}