{"id":"https://openalex.org/W4321448327","doi":"https://doi.org/10.14778/3574245.3574261","title":"SubStrat","display_name":"SubStrat","publication_year":2022,"publication_date":"2022-12-01","ids":{"openalex":"https://openalex.org/W4321448327","doi":"https://doi.org/10.14778/3574245.3574261"},"language":"en","primary_location":{"id":"doi:10.14778/3574245.3574261","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3574245.3574261","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041000511","display_name":"Teddy Lazebnik","orcid":"https://orcid.org/0000-0002-7851-8147"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Teddy Lazebnik","raw_affiliation_strings":["University College London"],"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040655769","display_name":"Amit Somech","orcid":"https://orcid.org/0000-0002-2314-6542"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Amit Somech","raw_affiliation_strings":["Bar-Ilan University"],"affiliations":[{"raw_affiliation_string":"Bar-Ilan University","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037956466","display_name":"Abraham Itzhak Weinberg","orcid":"https://orcid.org/0000-0002-2505-9653"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Abraham Itzhak Weinberg","raw_affiliation_strings":["Bar-Ilan University"],"affiliations":[{"raw_affiliation_string":"Bar-Ilan University","institution_ids":["https://openalex.org/I13955877"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041000511"],"corresponding_institution_ids":["https://openalex.org/I45129253"],"apc_list":null,"apc_paid":null,"fwci":2.3863,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.9041814,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"16","issue":"4","first_page":"772","last_page":"780"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9998999834060669,"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":0.9998999834060669,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9979000091552734,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9919999837875366,"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","display_name":"Pipeline (software)","score":0.8453649282455444},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6896392107009888},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5577570796012878},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5549354553222656},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4755953252315521},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4317360520362854},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.4246995151042938},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42011559009552},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38838014006614685},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08518105745315552}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.8453649282455444},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6896392107009888},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5577570796012878},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5549354553222656},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4755953252315521},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4317360520362854},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4246995151042938},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42011559009552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38838014006614685},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08518105745315552},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3574245.3574261","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3574245.3574261","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W760598031","https://openalex.org/W1531368347","https://openalex.org/W1969906866","https://openalex.org/W2099799055","https://openalex.org/W2101234009","https://openalex.org/W2126668662","https://openalex.org/W2167101736","https://openalex.org/W2225156818","https://openalex.org/W2602753196","https://openalex.org/W2746842762","https://openalex.org/W2790634852","https://openalex.org/W2911788310","https://openalex.org/W2913593702","https://openalex.org/W2927733588","https://openalex.org/W2945790622","https://openalex.org/W2947459187","https://openalex.org/W2966284335","https://openalex.org/W2971428651","https://openalex.org/W3006913750","https://openalex.org/W3020531607","https://openalex.org/W3105982656","https://openalex.org/W3137081859","https://openalex.org/W3197684911","https://openalex.org/W3201904098","https://openalex.org/W3211229017","https://openalex.org/W4236979447","https://openalex.org/W4250503569","https://openalex.org/W4255361718","https://openalex.org/W4321359614","https://openalex.org/W6675354045","https://openalex.org/W6788106616"],"related_works":["https://openalex.org/W3037187668","https://openalex.org/W4234772502","https://openalex.org/W2380685755","https://openalex.org/W4205762803","https://openalex.org/W2252100032","https://openalex.org/W2963436428","https://openalex.org/W2535856026","https://openalex.org/W3171253712","https://openalex.org/W4386564352","https://openalex.org/W2952668426"],"abstract_inverted_index":{"Automated":[0],"machine":[1],"learning":[2],"(AutoML)":[3],"frameworks":[4,29],"have":[5],"become":[6,81],"important":[7],"tools":[8],"in":[9,57,199],"the":[10,18,23,64,76,96,115,137,143,147,154,166,200,203],"data":[11,97,129],"scientist's":[12],"arsenal,":[13],"as":[14],"they":[15],"dramatically":[16],"reduce":[17],"manual":[19],"work":[20],"devoted":[21],"to":[22,73,123],"construction":[24],"of":[25,34,59,110,136,202],"ML":[26,36,205],"pipelines.":[27],"Such":[28],"intelligently":[30],"search":[31],"among":[32],"millions":[33],"possible":[35],"pipelines":[37],"-":[38,50],"typically":[39],"containing":[40],"feature":[41],"engineering,":[42],"model":[43],"selection,":[44],"and":[45,51,108,150,180],"hyper":[46],"parameters":[47],"tuning":[48],"steps":[49],"finally":[52],"output":[53],"an":[54,90],"optimal":[55],"pipeline":[56,156],"terms":[58],"predictive":[60],"accuracy.":[61],"However,":[62],"when":[63],"dataset":[65],"is":[66],"large,":[67],"each":[68],"individual":[69],"configuration":[70,101],"takes":[71],"longer":[72],"execute,":[74],"therefore":[75],"overall":[77],"AutoML":[78,91,106,144,163,176],"running":[79,187],"times":[80,188],"increasingly":[82],"high.":[83],"To":[84],"this":[85],"end,":[86],"we":[87],"present":[88],"SubStrat,":[89],"optimization":[92],"strategy":[93],"that":[94,131,183],"tackles":[95],"size,":[98],"rather":[99],"than":[100],"space.":[102],"It":[103,140],"wraps":[104],"existing":[105],"tools,":[107],"instead":[109],"executing":[111,158],"them":[112],"directly":[113],"on":[114,146,165,173],"entire":[116],"dataset,":[117],"SubStrat":[118,184],"uses":[119],"a":[120,125,133,159,195],"genetic-based":[121],"algorithm":[122],"find":[124],"small":[126,148],"yet":[127],"representative":[128],"subset":[130],"preserves":[132],"particular":[134],"characteristic":[135],"full":[138],"data.":[139],"then":[141],"employs":[142],"tool":[145],"subset,":[149],"finally,":[151],"it":[152],"refines":[153],"resulting":[155,204],"by":[157,189],"restricted,":[160],"much":[161],"shorter,":[162],"process":[164],"large":[167],"dataset.":[168],"Our":[169],"experimental":[170],"results,":[171],"performed":[172],"three":[174],"popular":[175],"frameworks,":[177],"Auto-Sklearn,":[178],"TPOT,":[179],"H2O":[181],"show":[182],"reduces":[185],"their":[186],"76.3%":[190],"(on":[191],"average),":[192],"with":[193],"only":[194],"4.15%":[196],"average":[197],"decrease":[198],"accuracy":[201],"pipeline.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2023-02-22T00:00:00"}