{"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/A5032555732","display_name":"Patricio Cerda","orcid":"https://orcid.org/0000-0002-0823-8174"},"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":false,"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)"],"raw_orcid":"https://orcid.org/0000-0001-5184-6362","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)"],"raw_orcid":null,"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":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2045,"currency":"USD","value_usd":2045},"apc_paid":null,"fwci":7.8196,"has_fulltext":false,"cited_by_count":118,"citation_normalized_percentile":{"value":0.97817345,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"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":"2331-8422","issn":["2331-8422"],"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/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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, ⟨10.1109/TKDE.2020.2992529⟩","raw_type":"info:eu-repo/semantics/article"}],"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":"2331-8422","issn":["2331-8422"],"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":[{"id":"https://openalex.org/G232567176","display_name":"Data integration and cleaning for statistical analysis","funder_award_id":"ANR-17-CE23-0018","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"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":[1,179],"usually":[2],"require":[3,148],"vector":[4],"representations":[5],"of":[6,20,48,88],"categorical":[7,51,127],"variables,":[8],"using":[9],"for":[10,30,74,85,190],"instanceone-hot":[11],"encoding.":[12],"This":[13],"strategy":[14],"breaks":[15],"down":[16],"when":[17],"the":[18,131,137,141,156,160,188],"number":[19],"categories":[21,173],"grows,":[22],"as":[23,144,163,168,185],"it":[24,145,164],"creates":[25],"high-dimensional":[26],"feature":[27,176,191],"vectors.":[28],"Additionally,":[29],"string":[31,50,75,89,183],"entries,":[32],"one-hot":[33,169],"encoding":[34,47,72,170],"does":[35,146],"not":[36,147],"capture":[37],"morphological":[38],"information":[39],"in":[40],"their":[41],"representation.":[42],"Here,":[43],"we":[44],"seek":[45],"low-dimensional":[46],"high-cardinality":[49,126],"variables.":[52,128],"Ideally,":[53],"these":[54,120],"should":[55],"be:":[56],"scalable":[57,109],"to":[58,62,104],"many":[59],"categories;":[60],"interpretable":[61],"end":[63],"users;":[64],"and":[65,82,110,115],"facilitate":[66],"statistical":[67],"analysis.":[68],"We":[69,91,129],"introduce":[70],"two":[71],"approaches":[73,107],"categories:":[76],"aGamma-Poisson":[77],"matrix":[78],"factorizationon":[79],"substring":[80],"counts,":[81],"amin-hash":[83],"encoder,":[84],"fast":[86],"approximation":[87],"similarities.":[90],"show":[92,118],"that":[93,101,119],"min-hash":[94,138],"turns":[95],"set":[96],"inclusions":[97],"into":[98],"inequality":[99],"relations":[100],"are":[102,108],"easier":[103],"learn.":[105],"Both":[106,178],"streamable.":[111],"Experiments":[112],"on":[113,171,182],"real":[114],"simulated":[116],"data":[117,150,194],"methods":[121],"improve":[122],"supervised":[123],"learning":[124],"with":[125,174],"recommend":[130],"following:":[132],"if":[133,152],"scalability":[134],"is":[135,140,154,159],"central,":[136],"encoder":[139],"best":[142,161],"option":[143],"any":[149],"fit;":[151],"interpretability":[153],"important,":[155],"Gamma-Poisson":[157],"factorization":[158],"alternative,":[162],"can":[165],"be":[166],"interpreted":[167],"inferred":[172],"informative":[175],"names.":[177],"enable":[180],"autoML":[181],"entries":[184],"they":[186],"remove":[187],"need":[189],"engineering":[192],"or":[193],"cleaning.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"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":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}