{"id":"https://openalex.org/W2954052001","doi":"https://doi.org/10.1109/tkde.2020.2992529","title":"Encoding High-Cardinality String Categorical Variables","display_name":"Encoding High-Cardinality String Categorical Variables","publication_year":2020,"publication_date":"2020-05-04","ids":{"openalex":"https://openalex.org/W2954052001","doi":"https://doi.org/10.1109/tkde.2020.2992529","mag":"2954052001"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2020.2992529","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2020.2992529","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1907.01860","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015283389","display_name":"Patricio Cerda","orcid":"https://orcid.org/0000-0001-5184-6362"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I2738703131","display_name":"Commissariat \u00e0 l'\u00c9nergie Atomique et aux \u00c9nergies Alternatives","ror":"https://ror.org/00jjx8s55","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131"]},{"id":"https://openalex.org/I4210128565","display_name":"CEA Paris-Saclay","ror":"https://ror.org/03n15ch10","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131","https://openalex.org/I277688954","https://openalex.org/I4210128565"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Patricio Cerda","raw_affiliation_strings":["Inria, Parietal team, Rocquencourt, France","PARIETAL - Modelling brain structure, function and variability based on high-field MRI data (Neurospin, CEA Saclay, B\u00e2timent 145, 91191 Gif-sur-Yvette Cedex - France)"],"affiliations":[{"raw_affiliation_string":"Inria, Parietal team, Rocquencourt, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"PARIETAL - Modelling brain structure, function and variability based on high-field MRI data (Neurospin, CEA Saclay, B\u00e2timent 145, 91191 Gif-sur-Yvette Cedex - France)","institution_ids":["https://openalex.org/I2738703131","https://openalex.org/I4210128565"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074733625","display_name":"Ga\u00ebl Varoquaux","orcid":"https://orcid.org/0000-0003-1076-5122"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gael Varoquaux","raw_affiliation_strings":["Inria, Parietal team, Rocquencourt, France","NEUROSPIN - Service NEUROSPIN (France)"],"affiliations":[{"raw_affiliation_string":"Inria, Parietal team, Rocquencourt, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"NEUROSPIN - Service NEUROSPIN (France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5015283389"],"corresponding_institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I2738703131","https://openalex.org/I4210128565"],"apc_list":null,"apc_paid":null,"fwci":7.4755,"has_fulltext":false,"cited_by_count":110,"citation_normalized_percentile":{"value":0.97741153,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"34","issue":"3","first_page":"1164","last_page":"1176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing 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/T12535","display_name":"Machine Learning and Data Classification","score":0.9965999722480774,"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/string","display_name":"String (physics)","score":0.6846726536750793},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.6565427780151367},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6166380643844604},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.606019914150238},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5464526414871216},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5224282145500183},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4444180727005005},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.4181169867515564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3804601728916168},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.307995080947876},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.281873494386673},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2652685046195984},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11654019355773926},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10722777247428894}],"concepts":[{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6846726536750793},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6565427780151367},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6166380643844604},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.606019914150238},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5464526414871216},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5224282145500183},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4444180727005005},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.4181169867515564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3804601728916168},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.307995080947876},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.281873494386673},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2652685046195984},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11654019355773926},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10722777247428894},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tkde.2020.2992529","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2020.2992529","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1907.01860","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.01860","pdf_url":"https://arxiv.org/pdf/1907.01860","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:HAL:hal-02171256v3","is_oa":true,"landing_page_url":"https://hal.inria.fr/hal-02171256","pdf_url":null,"source":{"id":"https://openalex.org/S4406922276","display_name":"INRIA a CCSD electronic archive server","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal.inria.fr/hal-02171256","raw_type":"info:eu-repo/semantics/preprint"},{"id":"pmh:oai:HAL:hal-02171256v5","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-02171256","pdf_url":null,"source":{"id":"https://openalex.org/S4406922466","display_name":"SPIRE - Sciences Po Institutional REpository","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering, In press, &#x27E8;10.1109/TKDE.2020.2992529&#x27E9;","raw_type":"Journal articles"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1907.01860","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.01860","pdf_url":"https://arxiv.org/pdf/1907.01860","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W114869232","https://openalex.org/W1502624642","https://openalex.org/W1502916507","https://openalex.org/W1530010412","https://openalex.org/W1537946535","https://openalex.org/W1547612978","https://openalex.org/W1565746575","https://openalex.org/W1610496399","https://openalex.org/W1614298861","https://openalex.org/W1974758710","https://openalex.org/W1986966428","https://openalex.org/W1990836268","https://openalex.org/W2037757210","https://openalex.org/W2041614298","https://openalex.org/W2055906546","https://openalex.org/W2058269967","https://openalex.org/W2066102695","https://openalex.org/W2067393637","https://openalex.org/W2070996757","https://openalex.org/W2081193615","https://openalex.org/W2102636708","https://openalex.org/W2108991785","https://openalex.org/W2113651538","https://openalex.org/W2117756735","https://openalex.org/W2132069633","https://openalex.org/W2144902422","https://openalex.org/W2158997610","https://openalex.org/W2159401492","https://openalex.org/W2162833336","https://openalex.org/W2171313960","https://openalex.org/W2250539671","https://openalex.org/W2295598076","https://openalex.org/W2411707397","https://openalex.org/W2493916176","https://openalex.org/W2749093116","https://openalex.org/W2752172973","https://openalex.org/W2962772361","https://openalex.org/W2963105378","https://openalex.org/W2963341956","https://openalex.org/W2963905884","https://openalex.org/W2964022491","https://openalex.org/W2979473749","https://openalex.org/W2986888662","https://openalex.org/W3102476541","https://openalex.org/W3120740533","https://openalex.org/W3143596294","https://openalex.org/W3146259567","https://openalex.org/W4213308398","https://openalex.org/W4239677523","https://openalex.org/W4242744113","https://openalex.org/W4285719527","https://openalex.org/W4300601563","https://openalex.org/W6604605561","https://openalex.org/W6628353318","https://openalex.org/W6629956336","https://openalex.org/W6636177537","https://openalex.org/W6636510571","https://openalex.org/W6677106874","https://openalex.org/W6680012447","https://openalex.org/W6681302627","https://openalex.org/W6684050148","https://openalex.org/W6743384090","https://openalex.org/W6747248625","https://openalex.org/W6750729320"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W4390569940","https://openalex.org/W2888392564","https://openalex.org/W4361193272","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W2806259446","https://openalex.org/W2963326959","https://openalex.org/W4312407344","https://openalex.org/W4229333355"],"abstract_inverted_index":{"Statistical":[0],"models":[1,191],"usually":[2],"require":[3,160],"vector":[4],"representations":[5],"of":[6,24,52,100],"categorical":[7,55,139],"variables,":[8],"using":[9],"for":[10,34,78,97,202],"instance":[11],"<italic":[12,82,92],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[13,83,93],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">one-hot":[14],"encoding</i>":[15],".":[16],"This":[17],"strategy":[18],"breaks":[19],"down":[20],"when":[21],"the":[22,143,149,153,168,172,200],"number":[23],"categories":[25,185],"grows,":[26],"as":[27,156,175,180,197],"it":[28,157,176],"creates":[29],"high-dimensional":[30],"feature":[31,188,203],"vectors.":[32],"Additionally,":[33],"string":[35,54,79,101,195],"entries,":[36],"one-hot":[37,181],"encoding":[38,51,76,182],"does":[39,158],"not":[40,159],"capture":[41],"morphological":[42],"information":[43],"in":[44],"their":[45],"representation.":[46],"Here,":[47],"we":[48],"seek":[49],"low-dimensional":[50],"high-cardinality":[53,138],"variables.":[56,140],"Ideally,":[57],"these":[58,132],"should":[59],"be:":[60],"scalable":[61,121],"to":[62,66,116],"many":[63],"categories;":[64],"interpretable":[65],"end":[67],"users;":[68],"and":[69,90,122,127],"facilitate":[70],"statistical":[71],"analysis.":[72],"We":[73,103,141],"introduce":[74],"two":[75],"approaches":[77,119],"categories:":[80],"a":[81,91],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Gamma-Poisson":[84],"matrix":[85],"factorization</i>":[86],"on":[87,125,183,194],"substring":[88],"counts,":[89],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">min-hash":[94],"encoder</i>":[95],",":[96],"fast":[98],"approximation":[99],"similarities.":[102],"show":[104,130],"that":[105,113,131],"min-hash":[106,150],"turns":[107],"set":[108],"inclusions":[109],"into":[110],"inequality":[111],"relations":[112],"are":[114,120],"easier":[115],"learn.":[117],"Both":[118,190],"streamable.":[123],"Experiments":[124],"real":[126],"simulated":[128],"data":[129,162,206],"methods":[133],"improve":[134],"supervised":[135],"learning":[136],"with":[137,186],"recommend":[142],"following:":[144],"if":[145,164],"scalability":[146],"is":[147,152,166,171],"central,":[148],"encoder":[151],"best":[154,173],"option":[155],"any":[161],"fit;":[163],"interpretability":[165],"important,":[167],"Gamma-Poisson":[169],"factorization":[170],"alternative,":[174],"can":[177],"be":[178],"interpreted":[179],"inferred":[184],"informative":[187],"names.":[189],"enable":[192],"autoML":[193],"entries":[196],"they":[198],"remove":[199],"need":[201],"engineering":[204],"or":[205],"cleaning.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}