{"id":"https://openalex.org/W4289655997","doi":"https://doi.org/10.1109/icde53745.2022.00294","title":"Farming Your ML-based Query Optimizer's Food","display_name":"Farming Your ML-based Query Optimizer's Food","publication_year":2022,"publication_date":"2022-05-01","ids":{"openalex":"https://openalex.org/W4289655997","doi":"https://doi.org/10.1109/icde53745.2022.00294"},"language":"en","primary_location":{"id":"doi:10.1109/icde53745.2022.00294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde53745.2022.00294","pdf_url":null,"source":{"id":"https://openalex.org/S4363607857","display_name":"2022 IEEE 38th International Conference on Data Engineering (ICDE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 38th International Conference on Data Engineering (ICDE)","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/A5024438696","display_name":"Robin van de Water","orcid":"https://orcid.org/0000-0002-2895-4872"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Robin Van De Water","raw_affiliation_strings":["Hasso Plattner Institut (HPI)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institut (HPI)","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081839375","display_name":"Francesco Ventura","orcid":"https://orcid.org/0000-0003-3398-8265"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Francesco Ventura","raw_affiliation_strings":["Technische Universität Berlin (TU Berlin)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universität Berlin (TU Berlin)","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068470780","display_name":"Zoi Kaoudi","orcid":"https://orcid.org/0000-0003-4520-5360"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zoi Kaoudi","raw_affiliation_strings":["Technische Universität Berlin (TU Berlin)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universität Berlin (TU Berlin)","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083942725","display_name":"Jorge-Arnulfo Quian\u00e9-Ruiz","orcid":"https://orcid.org/0000-0002-9001-825X"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jorge-Arnulfo Quiane-Ruiz","raw_affiliation_strings":["Technische Universität Berlin (TU Berlin)","DFKI GmbH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universität Berlin (TU Berlin)","institution_ids":["https://openalex.org/I4577782"]},{"raw_affiliation_string":"DFKI GmbH","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002413906","display_name":"Volker Markl","orcid":"https://orcid.org/0009-0009-0964-026X"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]},{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Volker Markl","raw_affiliation_strings":["Technische Universität Berlin (TU Berlin)","DFKI GmbH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universität Berlin (TU Berlin)","institution_ids":["https://openalex.org/I4577782"]},{"raw_affiliation_string":"DFKI GmbH","institution_ids":["https://openalex.org/I33256026"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5024438696"],"corresponding_institution_ids":["https://openalex.org/I143288331"],"apc_list":null,"apc_paid":null,"fwci":0.4156,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.57455606,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3186","last_page":"3189"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9983999729156494,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9983999729156494,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9980999827384949,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8769744634628296},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7036518454551697},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.7030762434005737},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.6380975842475891},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5688515901565552},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5650606155395508},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.42573487758636475},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.4198117256164551},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4039406180381775},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38723787665367126},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08743536472320557}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8769744634628296},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7036518454551697},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.7030762434005737},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.6380975842475891},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5688515901565552},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5650606155395508},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.42573487758636475},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.4198117256164551},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4039406180381775},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38723787665367126},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08743536472320557},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icde53745.2022.00294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde53745.2022.00294","pdf_url":null,"source":{"id":"https://openalex.org/S4363607857","display_name":"2022 IEEE 38th International Conference on Data Engineering (ICDE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 38th International Conference on Data Engineering (ICDE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324094","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2769041395","https://openalex.org/W2890276152","https://openalex.org/W2911464154","https://openalex.org/W2918066172","https://openalex.org/W2959716049","https://openalex.org/W2962862931","https://openalex.org/W2970148517","https://openalex.org/W2991530444","https://openalex.org/W3031623163","https://openalex.org/W3099273181","https://openalex.org/W3105457604","https://openalex.org/W3124277639","https://openalex.org/W3139469262","https://openalex.org/W6737947904","https://openalex.org/W6753577402"],"related_works":["https://openalex.org/W2607929079","https://openalex.org/W1485630101","https://openalex.org/W2498017833","https://openalex.org/W2068245803","https://openalex.org/W2329086085","https://openalex.org/W2314755979","https://openalex.org/W112744582","https://openalex.org/W2390710122","https://openalex.org/W2983785000","https://openalex.org/W1533823869"],"abstract_inverted_index":{"Machine":[0],"learning":[1,93,108],"(ML)":[2],"is":[3,44],"becoming":[4],"a":[5,41,45,112,183],"core":[6],"component":[7],"in":[8,127,166],"query":[9,24,78],"optimizers,":[10],"e.g.,":[11],"to":[12,60,80,89,110,116,138,163,180],"estimate":[13],"costs":[14],"or":[15,26,33],"cardinalities.":[16],"This":[17],"means":[18],"large":[19],"heterogeneous":[20],"sets":[21],"of":[22,114,135,142],"labeled":[23],"plans":[25,29],"jobs":[27,56,115,145,179],"(i.e.,":[28],"with":[30,190],"their":[31,95,191],"runtime":[32],"cardinality":[34],"output)":[35],"are":[36],"needed.":[37],"However,":[38],"collecting":[39],"such":[40],"training":[42,74,86,187],"dataset":[43],"very":[46],"tedious":[47],"and":[48,57,72,101,119,146,160,185],"time-consuming":[49],"task:":[50],"It":[51,104],"requires":[52],"both":[53,176],"developing":[54],"numerous":[55],"executing":[58],"them":[59,148],"acquire":[61],"ground-truth":[62],"labels.":[63],"We":[64,154],"demonstrate":[65],"Datafarm,a":[66],"novel":[67],"framework":[68],"for":[69,76],"efficiently":[70],"generating":[71,85],"labeling":[73],"data":[75,87,188],"ML-based":[77],"optimizers":[79],"overcome":[81],"these":[82],"issues.":[83],"Datafarmenables":[84],"tailored":[88],"users'":[90],"needs":[91],"by":[92],"from":[94],"existing":[96],"workload":[97],"patterns,":[98],"input":[99],"data,":[100],"computational":[102],"resources.":[103],"uses":[105],"an":[106,167,171],"active":[107],"approach":[109],"determine":[111],"subset":[113],"be":[117],"executed":[118],"encloses":[120],"the":[121,124,143,150,164,177,186],"human":[122],"into":[123],"loop,":[125],"resulting":[126],"higher":[128],"quality":[129],"data.":[130],"The":[131],"graphical":[132],"user":[133],"interface":[134],"Datafarmallows":[136],"users":[137,157,173],"get":[139],"informative":[140],"details":[141],"generated":[144,178],"guides":[147],"through":[149],"generation":[151],"process":[152],"step-by-step.":[153],"show":[155],"how":[156],"can":[158,174],"intervene":[159],"provide":[161],"feedback":[162],"system":[165],"iterative":[168],"fashion.":[169],"As":[170],"output,":[172],"download":[175],"use":[181],"as":[182],"benchmark":[184],"(jobs":[189],"labels).":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-20T08:49:12.498775","created_date":"2025-10-10T00:00:00"}