{"id":"https://openalex.org/W4200609229","doi":"https://doi.org/10.1109/works54523.2021.00013","title":"A Performance Characterization of Scientific Machine Learning Workflows","display_name":"A Performance Characterization of Scientific Machine Learning Workflows","publication_year":2021,"publication_date":"2021-11-01","ids":{"openalex":"https://openalex.org/W4200609229","doi":"https://doi.org/10.1109/works54523.2021.00013"},"language":"en","primary_location":{"id":"doi:10.1109/works54523.2021.00013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/works54523.2021.00013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Workflows in Support of Large-Scale Science (WORKS)","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/A5024828367","display_name":"Patrycja Krawczuk","orcid":"https://orcid.org/0000-0003-4860-9619"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Patrycja Krawczuk","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, Marina Del Rey, CA, USA","University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Marina Del Rey, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016335226","display_name":"George Papadimitriou","orcid":"https://orcid.org/0000-0001-9384-5034"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Papadimitriou","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, Marina Del Rey, CA, USA","University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Marina Del Rey, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016986076","display_name":"Ryan Tanaka","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan Tanaka","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, Marina Del Rey, CA, USA"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Marina Del Rey, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085537957","display_name":"Tu Mai Anh","orcid":"https://orcid.org/0000-0002-2419-2305"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tu Mai Anh Do","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, Marina Del Rey, CA, USA","University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Marina Del Rey, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089069657","display_name":"Srujana Subramanya","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srujana Subramanya","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071730756","display_name":"Shubham Nagarkar","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shubham Nagarkar","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101428943","display_name":"Aditi Jain","orcid":"https://orcid.org/0000-0002-0236-9683"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aditi Jain","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068188994","display_name":"Kelsie Lam","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kelsie Lam","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, Marina Del Rey, CA, USA"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Marina Del Rey, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063480283","display_name":"Anirban Mandal","orcid":"https://orcid.org/0000-0001-5145-8618"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]},{"id":"https://openalex.org/I69048370","display_name":"Renaissance Computing Institute","ror":"https://ror.org/01s91ey96","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535","https://openalex.org/I170897317","https://openalex.org/I69048370"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anirban Mandal","raw_affiliation_strings":["Renaissance Computing Institute, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"],"affiliations":[{"raw_affiliation_string":"Renaissance Computing Institute, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA","institution_ids":["https://openalex.org/I69048370","https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081878727","display_name":"Lo\u00efc Pottier","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Loic Pottier","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, Marina Del Rey, CA, USA"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Marina Del Rey, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031941569","display_name":"Ewa Deelman","orcid":"https://orcid.org/0000-0001-5106-503X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ewa Deelman","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, Marina Del Rey, CA, USA","University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Marina Del Rey, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5024828367"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.9371,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.88446402,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"58","last_page":"65"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9769999980926514,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9717000126838684,"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/workflow","display_name":"Workflow","score":0.9403338432312012},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7973777055740356},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.618511974811554},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5100436806678772},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.45930182933807373},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44386643171310425},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4184703826904297},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.40329304337501526},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.392220675945282},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3813941478729248},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.22368279099464417},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07740256190299988}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.9403338432312012},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7973777055740356},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.618511974811554},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5100436806678772},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.45930182933807373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44386643171310425},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4184703826904297},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40329304337501526},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.392220675945282},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3813941478729248},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.22368279099464417},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07740256190299988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/works54523.2021.00013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/works54523.2021.00013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Workflows in Support of Large-Scale Science (WORKS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G3908005591","display_name":null,"funder_award_id":"#DE-SC0012636,#DE-SC0022328","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8031589789","display_name":null,"funder_award_id":"#1664162","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1974752004","https://openalex.org/W2078962046","https://openalex.org/W2085980508","https://openalex.org/W2126623642","https://openalex.org/W2128548442","https://openalex.org/W2148317584","https://openalex.org/W2189465200","https://openalex.org/W2250539671","https://openalex.org/W2605897695","https://openalex.org/W2613409207","https://openalex.org/W2786095067","https://openalex.org/W2798683079","https://openalex.org/W2883005809","https://openalex.org/W2906137127","https://openalex.org/W2915854813","https://openalex.org/W2949676527","https://openalex.org/W2954353134","https://openalex.org/W2963304552","https://openalex.org/W2983617330","https://openalex.org/W2987607480","https://openalex.org/W2995564009","https://openalex.org/W3008227512","https://openalex.org/W3016820838","https://openalex.org/W3088241762","https://openalex.org/W3110783234","https://openalex.org/W3118693078","https://openalex.org/W3137587712","https://openalex.org/W6687322159"],"related_works":["https://openalex.org/W2770234245","https://openalex.org/W96612179","https://openalex.org/W4229499248","https://openalex.org/W2566006169","https://openalex.org/W1567818861","https://openalex.org/W2987774938","https://openalex.org/W4256492088","https://openalex.org/W632915154","https://openalex.org/W2055733372","https://openalex.org/W3022067003"],"abstract_inverted_index":{"Scientific":[0],"workflows":[1,50,97,103,111,188,209],"are":[2,63],"one":[3],"of":[4,8,32,115],"the":[5,58,149,173],"well-established":[6],"pillars":[7],"modern":[9,48],"large-scale":[10],"computational":[11],"science.":[12],"More":[13],"recently,":[14],"scientists":[15],"have":[16,145],"started":[17],"to":[18,28,83,91,137],"leverage":[19],"machine":[20],"learning":[21],"(ML)":[22],"capabilities":[23],"in":[24,68,113],"their":[25,221],"workflows,":[26,34,79,132],"leading":[27],"a":[29,124],"new":[30],"category":[31],"scientific":[33,37,77,95,102,208],"denoted":[35],"as":[36],"ML":[38,40,49,78,96,110,211],"workflows.":[39,225],"is":[41],"not":[42,64],"only":[43],"about":[44],"training":[45,59],"and":[46,86,118,141,181,190,202,213],"inference,":[47,85],"also":[51],"involve":[52],"complex":[53],"data":[54,81,119,165],"processing":[55,140],"steps":[56],"before":[57],"can":[60,108,219],"start,":[61],"which":[62,144,163],"often":[65],"accounted":[66],"for":[67,160,223],"most":[69],"performance":[70,174,189,204],"studies.":[71],"In":[72],"this":[73],"work,":[74],"we":[75,107,171,198],"consider":[76],"from":[80,99,134],"pre-processing":[82],"training,":[84],"model":[87],"evaluation.":[88],"We":[89,128,154],"aim":[90],"explore":[92],"(i)":[93],"how":[94,106,183,214],"differ":[98],"more":[100],"traditional":[101,215],"and;":[104],"(ii)":[105],"characterize":[109],"both":[112],"terms":[114],"execution":[116],"time":[117],"movements":[120,166],"when":[121,176,192,206],"executing":[122],"on":[123,194],"target":[125],"cloud":[126,151,195],"platform.":[127],"select":[129],"three":[130],"representative":[131],"ranging":[133],"image":[135,142],"classification":[136],"natural":[138],"language":[139],"segmentation,":[143],"been":[146],"executed":[147],"using":[148],"academic":[150],"platform,":[152],"Chameleon.":[153],"build":[155],"four":[156],"realistic":[157],"deployment":[158],"scenarios":[159],"each":[161],"workflow,":[162],"stress":[164],"during":[167],"workflow":[168,216],"executions.":[169],"Then,":[170],"compare":[172],"observed":[175],"utilizing":[177],"these":[178],"different":[179,184],"configurations":[180],"study":[182],"settings":[185],"impact":[186],"overall":[187],"efficiency":[191],"running":[193],"infrastructures.":[196],"Finally,":[197],"summarize":[199],"our":[200],"findings":[201],"discuss":[203],"impacts":[205],"augmenting":[207],"with":[210],"techniques":[212],"management":[217],"systems":[218],"improve":[220],"support":[222],"such":[224]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
