{"id":"https://openalex.org/W4416252033","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228307","title":"PIPES: A Meta-dataset of Machine Learning Pipelines","display_name":"PIPES: A Meta-dataset of Machine Learning Pipelines","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416252033","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228307"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5030825181","display_name":"Cynthia Moreira Maia","orcid":null},"institutions":[{"id":"https://openalex.org/I79889768","display_name":"Universidade Federal de Alagoas","ror":"https://ror.org/00dna7t83","country_code":"BR","type":"education","lineage":["https://openalex.org/I79889768"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Cynthia Moreira Maia","raw_affiliation_strings":["Universidade Federal de Alagoas,Instituto de Computação,Maceió,Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade Federal de Alagoas,Instituto de Computação,Maceió,Brazil","institution_ids":["https://openalex.org/I79889768"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036383947","display_name":"Lucas Amorim","orcid":"https://orcid.org/0000-0003-2725-6527"},"institutions":[{"id":"https://openalex.org/I79889768","display_name":"Universidade Federal de Alagoas","ror":"https://ror.org/00dna7t83","country_code":"BR","type":"education","lineage":["https://openalex.org/I79889768"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Lucas B. V. de Amorim","raw_affiliation_strings":["Universidade Federal de Alagoas,Instituto de Computação,Maceió,Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade Federal de Alagoas,Instituto de Computação,Maceió,Brazil","institution_ids":["https://openalex.org/I79889768"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084140678","display_name":"George D. C. Cavalcanti","orcid":"https://orcid.org/0000-0001-7714-2283"},"institutions":[{"id":"https://openalex.org/I79889768","display_name":"Universidade Federal de Alagoas","ror":"https://ror.org/00dna7t83","country_code":"BR","type":"education","lineage":["https://openalex.org/I79889768"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"George D. C. Cavalcanti","raw_affiliation_strings":["Universidade Federal de Alagoas,Instituto de Computação,Maceió,Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade Federal de Alagoas,Instituto de Computação,Maceió,Brazil","institution_ids":["https://openalex.org/I79889768"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019553116","display_name":"Rafael M. O. Cruz","orcid":"https://orcid.org/0000-0001-9446-1040"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rafael M. O. Cruz","raw_affiliation_strings":["Université du Québec,École de Technologie Supérieure,Montréal,Canada"],"affiliations":[{"raw_affiliation_string":"Université du Québec,École de Technologie Supérieure,Montréal,Canada","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030825181"],"corresponding_institution_ids":["https://openalex.org/I79889768"],"apc_list":null,"apc_paid":null,"fwci":2.8331,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.93090303,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9891999959945679,"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":0.9891999959945679,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0017999999690800905,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.0005000000237487257,"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/pipeline-transport","display_name":"Pipeline transport","score":0.7131999731063843},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6909999847412109},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6503000259399414},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6272000074386597},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.5386000275611877},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.47769999504089355},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4027999937534332},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.38989999890327454}],"concepts":[{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.7131999731063843},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6909999847412109},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6796000003814697},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6503000259399414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6330000162124634},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6272000074386597},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.5386000275611877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5175999999046326},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49950000643730164},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.47769999504089355},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4027999937534332},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.38989999890327454},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.36149999499320984},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2574000060558319}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:espace2.etsmtl.ca:33115","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402392","display_name":"Espace \u00c9TS (ETS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1341030882","host_organization_name":"Educational Testing Service","host_organization_lineage":["https://openalex.org/I1341030882"],"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":"Non \u00e9valu\u00e9 par les pairs"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1495775210","https://openalex.org/W1894116512","https://openalex.org/W1974752961","https://openalex.org/W2010770252","https://openalex.org/W2027308928","https://openalex.org/W2089213632","https://openalex.org/W2101234009","https://openalex.org/W2132862423","https://openalex.org/W2153380237","https://openalex.org/W2163212577","https://openalex.org/W2563364594","https://openalex.org/W2817593237","https://openalex.org/W2898576334","https://openalex.org/W2945790622","https://openalex.org/W2999917162","https://openalex.org/W3082548640","https://openalex.org/W3092248103","https://openalex.org/W4205556549","https://openalex.org/W4212979146","https://openalex.org/W4213308398","https://openalex.org/W4311543603","https://openalex.org/W4385421664","https://openalex.org/W4386212933","https://openalex.org/W4392157622","https://openalex.org/W4392401953"],"related_works":[],"abstract_inverted_index":{"Solutions":[0],"to":[1,98,120,145,174,198],"the":[2,11,31,104,125,137,153,163,200],"Algorithm":[3],"Selection":[4],"Problem":[5],"(ASP)":[6],"in":[7,40,66,80],"machine":[8,52],"learning":[9,53],"face":[10],"challenge":[12],"of":[13,51,58,107,114,124,128,139,170],"high":[14],"computational":[15],"costs":[16],"associated":[17],"with":[18],"evaluating":[19],"various":[20],"algorithms'":[21],"performances":[22],"on":[23,88,152],"a":[24,89,112],"given":[25],"dataset.":[26],"To":[27,102],"mitigate":[28],"this":[29],"cost,":[30],"meta-learning":[32,201],"field":[33],"can":[34,195,212],"leverage":[35],"previously":[36],"executed":[37],"experiments":[38,84,115,140,194,211],"shared":[39],"online":[41],"repositories":[42],"such":[43,74],"as":[44,75,190],"OpenML.":[45],"OpenML":[46],"provides":[47],"an":[48,56,99],"extensive":[49],"collection":[50,113,169],"experiments.":[54],"However,":[55],"analysis":[57],"OpenML\u2019s":[59],"records":[60],"reveals":[61],"limitations.":[62],"It":[63,148],"lacks":[64],"diversity":[65,132],"pipelines,":[67],"specifically":[68],"when":[69],"exploring":[70],"data":[71,192],"preprocessing":[72],"steps/blocks,":[73],"scaling":[76],"or":[77],"imputation,":[78],"resulting":[79],"limited":[81],"representation.":[82],"Its":[83],"are":[85],"often":[86],"focused":[87],"few":[90],"popular":[91],"techniques":[92],"within":[93],"each":[94],"pipeline":[95,154],"block,":[96],"leading":[97],"imbalanced":[100],"sample.":[101],"overcome":[103],"observed":[105],"limitations":[106],"OpenML,":[108],"we":[109],"propose":[110],"PIPES,":[111],"involving":[116],"multiple":[117],"pipelines":[118,144,181],"designed":[119],"represent":[121],"all":[122,210],"combinations":[123],"selected":[126],"sets":[127],"techniques,":[129],"aiming":[130],"at":[131,215],"and":[133,157,162,179,182,193,209],"completeness.":[134],"PIPES":[135,184],"stores":[136],"results":[138,171],"performed":[141],"applying":[142],"9,408":[143],"300":[146],"datasets.":[147,183],"includes":[149],"detailed":[150],"information":[151],"blocks,":[155],"training":[156],"testing":[158],"times,":[159],"predictions,":[160],"performances,":[161],"eventual":[164],"error":[165],"messages.":[166],"This":[167],"comprehensive":[168],"allows":[172],"researchers":[173],"perform":[175],"analyses":[176],"across":[177],"diverse":[178],"representative":[180],"also":[185],"offers":[186],"potential":[187],"for":[188],"expansion,":[189],"additional":[191],"be":[196,213],"incorporated":[197],"support":[199],"community":[202],"further.":[203],"The":[204],"data,":[205],"code,":[206],"supplementary":[207],"material,":[208],"found":[214],"https://github.com/cynthiamaia/PIPES.git.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}