{"id":"https://openalex.org/W4386768649","doi":"https://doi.org/10.14778/3611540.3611606","title":"mlwhatif: What If You Could Stop Re-Implementing Your Machine Learning Pipeline Analyses over and over?","display_name":"mlwhatif: What If You Could Stop Re-Implementing Your Machine Learning Pipeline Analyses over and over?","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4386768649","doi":"https://doi.org/10.14778/3611540.3611606"},"language":"en","primary_location":{"id":"doi:10.14778/3611540.3611606","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3611540.3611606","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.uva.nl/ws/files/141104572/Mlwhatif.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081322278","display_name":"Stefan Grafberger","orcid":"https://orcid.org/0000-0002-9884-9517"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Stefan Grafberger","raw_affiliation_strings":["AIRLab, University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIRLab, University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066160649","display_name":"Shubha Guha","orcid":"https://orcid.org/0000-0002-9156-1561"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Shubha Guha","raw_affiliation_strings":["University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034924491","display_name":"Paul Groth","orcid":"https://orcid.org/0000-0003-0183-6910"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Paul Groth","raw_affiliation_strings":["University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090934117","display_name":"Sebastian Schelter","orcid":"https://orcid.org/0000-0003-4722-5840"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Sebastian Schelter","raw_affiliation_strings":["University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":1.4276,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.84660638,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"16","issue":"12","first_page":"4002","last_page":"4005"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9666000008583069,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9666000008583069,"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":0.953499972820282,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9420999884605408,"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":0.7718594670295715},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7313730716705322},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.6696361899375916},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.6193633675575256},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5949516296386719},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5872493386268616},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5770124197006226},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5631787776947021},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46043696999549866},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.45003741979599},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33887380361557007},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1289406716823578},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10266390442848206}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7718594670295715},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7313730716705322},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.6696361899375916},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.6193633675575256},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5949516296386719},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5872493386268616},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5770124197006226},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5631787776947021},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46043696999549866},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.45003741979599},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33887380361557007},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1289406716823578},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10266390442848206},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/3611540.3611606","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3611540.3611606","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:dare.uva.nl:publications/2aafa4da-add3-47d6-947f-12de274c93a6","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/mlwhatif-what-if-you-could-stop-reimplementing-your-machine-learning-pipeline-analyses-over-and-over(2aafa4da-add3-47d6-947f-12de274c93a6).html","pdf_url":"https://pure.uva.nl/ws/files/141104572/Mlwhatif.pdf","source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Grafberger, S, Guha, S, Groth, P & Schelter, S 2023, 'Mlwhatif: What If You Could Stop Re-Implementing Your Machine Learning Pipeline Analyses over and Over?', Proceedings of the VLDB Endowment, vol. 16, no. 12, pp. 4002\u20134005. https://doi.org/10.14778/3611540.3611606","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:dare.uva.nl:publications/2aafa4da-add3-47d6-947f-12de274c93a6","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/mlwhatif-what-if-you-could-stop-reimplementing-your-machine-learning-pipeline-analyses-over-and-over(2aafa4da-add3-47d6-947f-12de274c93a6).html","pdf_url":"https://pure.uva.nl/ws/files/141104572/Mlwhatif.pdf","source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Grafberger, S, Guha, S, Groth, P & Schelter, S 2023, 'Mlwhatif: What If You Could Stop Re-Implementing Your Machine Learning Pipeline Analyses over and Over?', Proceedings of the VLDB Endowment, vol. 16, no. 12, pp. 4002\u20134005. https://doi.org/10.14778/3611540.3611606","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386768649.pdf","grobid_xml":"https://content.openalex.org/works/W4386768649.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W2926314329"],"related_works":["https://openalex.org/W4248881655","https://openalex.org/W3092506759","https://openalex.org/W2952736244","https://openalex.org/W2373749036","https://openalex.org/W2899307613","https://openalex.org/W2367545121","https://openalex.org/W2360717114","https://openalex.org/W2382928216","https://openalex.org/W102552829","https://openalex.org/W2066954980"],"abstract_inverted_index":{"Software":[0],"systems":[1,33],"that":[2,20,118],"learn":[3],"from":[4],"data":[5,24,46,54,71,120,145,168,173,180],"with":[6,37,68],"machine":[7],"learning":[8],"(ML)":[9],"are":[10,34],"used":[11],"in":[12,31],"critical":[13],"decision-making":[14],"processes.":[15],"Unfortunately,":[16],"real-world":[17],"experience":[18],"shows":[19],"the":[21,60,105,108,138,162,170,177,195,200],"pipelines":[22,154],"for":[23,127,150,199],"preparation,":[25],"feature":[26],"encoding":[27],"and":[28,62,98,131,136,155,176,193],"model":[29],"training":[30],"ML":[32,87,129],"often":[35],"brittle":[36],"respect":[38,69],"to":[39,49,58,70,102,122,132],"their":[40],"input":[41],"data.":[42],"As":[43],"a":[44,80,90,95,116,151,165],"consequence,":[45],"scientists":[47,121,146],"have":[48],"run":[50],"different":[51,157],"kinds":[52],"of":[53,64,153,164,172,179],"centric":[55],"what-if":[56,77,125,158],"analyses":[57,78,126,159],"evaluate":[59],"robustness":[61,163],"reliability":[63],"such":[65],"pipelines,":[66],"e.g.,":[67],"errors":[72],"or":[73],"preprocessing":[74,181],"techniques.":[75],"These":[76],"follow":[79],"common":[81],"pattern:":[82],"they":[83],"take":[84],"an":[85,128],"existing":[86],"pipeline,":[88,130],"create":[89],"pipeline":[91,140,166,201],"variant":[92,101],"by":[93],"introducing":[94],"small":[96],"change,":[97],"execute":[99,137],"this":[100],"see":[103],"how":[104,144,190],"change":[106],"impacts":[107],"pipeline's":[109],"output":[110],"score.":[111],"We":[112,142],"recently":[113],"proposed":[114],"mlwhatif,":[115],"library":[117,204],"enables":[119],"declaratively":[123],"specify":[124],"automatically":[133],"generate,":[134],"optimize":[135],"required":[139,196],"variants.":[141],"demonstrate":[143,188],"can":[147],"leverage":[148],"mlwhatif":[149,191],"variety":[152],"three":[156],"focusing":[160],"on":[161,183],"against":[167],"errors,":[169],"impact":[171,178],"cleaning":[174],"operations,":[175],"operations":[182],"fairness.":[184],"In":[185],"particular,":[186],"we":[187],"step-by-step":[189],"generates":[192],"optimizes":[194],"execution":[197],"plans":[198],"analyses.":[202],"Our":[203],"is":[205],"publicly":[206],"available":[207],"at":[208],"https://github.com/stefan-grafberger/mlwhatif.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}