{"id":"https://openalex.org/W4400909768","doi":"https://doi.org/10.1109/icde60146.2024.00150","title":"AutoFeat: Transitive Feature Discovery over Join Paths","display_name":"AutoFeat: Transitive Feature Discovery over Join Paths","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4400909768","doi":"https://doi.org/10.1109/icde60146.2024.00150"},"language":"en","primary_location":{"id":"doi:10.1109/icde60146.2024.00150","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde60146.2024.00150","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 40th International Conference on Data Engineering (ICDE)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5044229035","display_name":"Andra Ionescu","orcid":"https://orcid.org/0000-0001-5113-8497"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Andra Ionescu","raw_affiliation_strings":["Delft University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108564855","display_name":"\u041a. \u041a. \u0412\u0430\u0441\u0438\u043b\u044c\u0435\u0432","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Kiril Vasilev","raw_affiliation_strings":["Delft University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066072200","display_name":"Florena Buse","orcid":"https://orcid.org/0009-0008-7225-6255"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Florena Buse","raw_affiliation_strings":["Delft University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046074866","display_name":"Rihan Hai","orcid":"https://orcid.org/0000-0002-3720-6585"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Rihan Hai","raw_affiliation_strings":["Delft University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002932353","display_name":"Asterios Katsifodimos","orcid":"https://orcid.org/0000-0002-6717-2945"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Asterios Katsifodimos","raw_affiliation_strings":["Delft University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1861","last_page":"1873"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9847000241279602,"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/T11106","display_name":"Data Management and Algorithms","score":0.9836999773979187,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/transitive-relation","display_name":"Transitive relation","score":0.7774193286895752},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.7479077577590942},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7036874890327454},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5926686525344849},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3783552348613739},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3314412832260132},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13647738099098206},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.10239946842193604}],"concepts":[{"id":"https://openalex.org/C191399111","wikidata":"https://www.wikidata.org/wiki/Q64861","display_name":"Transitive relation","level":2,"score":0.7774193286895752},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.7479077577590942},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7036874890327454},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5926686525344849},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3783552348613739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3314412832260132},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13647738099098206},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.10239946842193604},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icde60146.2024.00150","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde60146.2024.00150","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 40th International Conference on Data Engineering (ICDE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W12154863","https://openalex.org/W1485873552","https://openalex.org/W1661871015","https://openalex.org/W1995875735","https://openalex.org/W1996505782","https://openalex.org/W2006522651","https://openalex.org/W2017337590","https://openalex.org/W2066305262","https://openalex.org/W2118382442","https://openalex.org/W2121467460","https://openalex.org/W2130949063","https://openalex.org/W2149772057","https://openalex.org/W2156571267","https://openalex.org/W2157060173","https://openalex.org/W2257550357","https://openalex.org/W2403749440","https://openalex.org/W2562319768","https://openalex.org/W2743703549","https://openalex.org/W2795089200","https://openalex.org/W2798664493","https://openalex.org/W2889249015","https://openalex.org/W2912882859","https://openalex.org/W2948163032","https://openalex.org/W2950817225","https://openalex.org/W2964278775","https://openalex.org/W2970059736","https://openalex.org/W2998216295","https://openalex.org/W3014616325","https://openalex.org/W3032215537","https://openalex.org/W3037852608","https://openalex.org/W3129868498","https://openalex.org/W3164968002","https://openalex.org/W3174181645","https://openalex.org/W3174637548","https://openalex.org/W3176502563","https://openalex.org/W3196904276","https://openalex.org/W4287826698","https://openalex.org/W4289236186","https://openalex.org/W4289533982","https://openalex.org/W4367032190","https://openalex.org/W4379390735","https://openalex.org/W4385270264","https://openalex.org/W4385270278","https://openalex.org/W6630733370","https://openalex.org/W6636914306","https://openalex.org/W6682904970","https://openalex.org/W7006806681","https://openalex.org/W7038721187","https://openalex.org/W7066667914"],"related_works":["https://openalex.org/W4312527695","https://openalex.org/W2361167282","https://openalex.org/W4205996836","https://openalex.org/W1528932152","https://openalex.org/W2091342995","https://openalex.org/W2271118953","https://openalex.org/W2151692181","https://openalex.org/W3007067598","https://openalex.org/W2359420171","https://openalex.org/W1677394555"],"abstract_inverted_index":{"Can":[0],"we":[1],"automatically":[2],"discover":[3,34],"machine":[4],"learning":[5],"(ML)":[6],"features":[7,35,97,126,159],"in":[8,13,36,46,98,197],"a":[9,20,72,81,85],"large":[10],"data":[11,52,150,165,200],"lake":[12],"order":[14,99],"to":[15,33,94,100,110,130,192],"increase":[16],"the":[17,102,122,128,139,193],"accuracy":[18,112,186],"of":[19,59,113,125,141,160,171],"given":[21],"ML":[22,115,133],"model?":[23],"Existing":[24],"solutions":[25],"either":[26],"focus":[27],"on":[28,147,164,189],"simple":[29],"star":[30],"schemata,":[31],"failing":[32],"more":[37],"complex":[38],"real-world":[39,51,148],"schemata":[40],"or":[41],"consider":[42],"only":[43],"PK-FK":[44],"relationships":[45,62,174],"clean,":[47],"curated":[48],"databases.":[49],"However,":[50],"lakes":[53,166],"can":[54,157],"contain":[55],"long":[56],"join":[57,92,136],"paths":[58,93,137],"uncurated":[60,199],"joinability":[61,173],"resulting":[63],"from":[64],"automated":[65],"dataset":[66,172],"discovery":[67,76],"methods.":[68],"This":[69],"paper":[70],"proposes":[71],"novel":[73],"ranking-based":[74],"feature":[75],"method":[77],"called":[78],"AutoFeat.":[79],"Given":[80],"base":[82,103],"table":[83,104],"with":[84,105,167],"target":[86],"label,":[87],"AutoFeat":[88,117,153,182],"explores":[89],"multi-hop,":[90],"transitive":[91],"find":[95,158],"relevant":[96],"augment":[101],"additional":[106],"features,":[107],"ultimately":[108],"leading":[109],"increased":[111,169],"an":[114,132,168],"model.":[116],"is":[118,154,183],"general:":[119],"it":[120,156],"evaluates":[121],"predictive":[123,162],"power":[124,163],"without":[127],"need":[129],"train":[131],"model,":[134],"ranking":[135],"using":[138],"concepts":[140],"relevance":[142],"and":[143],"redundancy.":[144],"Our":[145],"experiments":[146],"open":[149],"show":[151],"that":[152],"efficient:":[155],"high":[161],"number":[170],"5x-44x":[175],"faster":[176],"than":[177],"baseline":[178,194],"approaches.":[179],"In":[180],"addition,":[181],"effective,":[184],"improving":[185],"by":[187],"16%":[188],"average":[190],"compared":[191],"approaches,":[195],"even":[196],"noisy,":[198],"lakes.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}