{"id":"https://openalex.org/W4281386293","doi":"https://doi.org/10.1145/3533028.3533303","title":"Towards data-centric what-if analysis for native machine learning pipelines","display_name":"Towards data-centric what-if analysis for native machine learning pipelines","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W4281386293","doi":"https://doi.org/10.1145/3533028.3533303"},"language":"en","primary_location":{"id":"doi:10.1145/3533028.3533303","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3533028.3533303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixth Workshop on Data Management for End-To-End Machine Learning","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.uva.nl/ws/files/142442217/3533028.3533303.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/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":1.1808,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.80323086,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9993000030517578,"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":0.9993000030517578,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9987999796867371,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9980000257492065,"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":0.8182779550552368},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.740101158618927},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.6842982172966003},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.553688645362854},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.522837221622467},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.48181357979774475},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.448383092880249},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40800607204437256},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.40033239126205444},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3911733329296112},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3741149604320526},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.11468884348869324},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11447027325630188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8182779550552368},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.740101158618927},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.6842982172966003},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.553688645362854},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.522837221622467},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.48181357979774475},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.448383092880249},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40800607204437256},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40033239126205444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3911733329296112},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3741149604320526},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.11468884348869324},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11447027325630188},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3533028.3533303","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3533028.3533303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixth Workshop on Data Management for End-To-End Machine Learning","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire/b64a62f4-ee4c-4414-aff2-3568b6bc00c4","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/towards-datacentric-whatif-analysis-for-native-machine-learning-pipelines(b64a62f4-ee4c-4414-aff2-3568b6bc00c4).html","pdf_url":"https://pure.uva.nl/ws/files/142442217/3533028.3533303.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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:dare.uva.nl:openaire/b64a62f4-ee4c-4414-aff2-3568b6bc00c4","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/towards-datacentric-whatif-analysis-for-native-machine-learning-pipelines(b64a62f4-ee4c-4414-aff2-3568b6bc00c4).html","pdf_url":"https://pure.uva.nl/ws/files/142442217/3533028.3533303.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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4281386293.pdf","grobid_xml":"https://content.openalex.org/works/W4281386293.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W2547386789","https://openalex.org/W2548122763","https://openalex.org/W2956281901","https://openalex.org/W3166873126","https://openalex.org/W3194157648","https://openalex.org/W4224952145"],"related_works":["https://openalex.org/W2000444236","https://openalex.org/W2384475851","https://openalex.org/W2353602216","https://openalex.org/W2367078749","https://openalex.org/W2381798600","https://openalex.org/W2351618306","https://openalex.org/W2133117170","https://openalex.org/W2999162218","https://openalex.org/W1995889332","https://openalex.org/W2390634956"],"abstract_inverted_index":{"An":[0],"important":[1],"task":[2],"of":[3,11,48,54,81,103],"data":[4,18,63,76],"scientists":[5],"is":[6],"to":[7,14,77,105],"understand":[8],"the":[9,17,20,42,46,52,79,98],"sensitivity":[10],"their":[12],"models":[13,21,73],"changes":[15],"in":[16],"that":[19,70],"are":[22],"trained":[23,72],"and":[24,35,39,65,74,84],"tested":[25],"upon.":[26],"Currently,":[27],"conducting":[28],"such":[29,82],"data-centric":[30,55],"what-if":[31,56],"analyses":[32],"requires":[33],"significant":[34],"costly":[36],"manual":[37],"development":[38],"testing":[40],"with":[41],"corresponding":[43],"chance":[44],"for":[45],"introduction":[47],"bugs.":[49],"We":[50],"discuss":[51],"problem":[53],"analysis":[57],"over":[58],"whole":[59],"ML":[60],"pipelines":[61],"(including":[62],"preparation":[64],"feature":[66],"encoding),":[67],"propose":[68],"optimisations":[69],"reuse":[71],"intermediate":[75],"reduce":[78],"runtime":[80,99],"analysis,":[83],"finally":[85],"conduct":[86],"preliminary":[87],"experiments":[88],"on":[89],"three":[90],"complex":[91],"example":[92],"pipelines,":[93],"where":[94],"our":[95],"approach":[96],"reduces":[97],"by":[100],"a":[101],"factor":[102],"up":[104],"six.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}