{"id":"https://openalex.org/W2805979482","doi":"https://doi.org/10.1007/s10994-018-5724-2","title":"Similarity encoding for learning with dirty categorical variables","display_name":"Similarity encoding for learning with dirty categorical variables","publication_year":2018,"publication_date":"2018-06-12","ids":{"openalex":"https://openalex.org/W2805979482","doi":"https://doi.org/10.1007/s10994-018-5724-2","mag":"2805979482"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-018-5724-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-018-5724-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-018-5724-2.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-018-5724-2.pdf","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/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Patricio Cerda","raw_affiliation_strings":["Inria, Parietal team, 1 Rue Honor\u00e9 d\u2019Estienne d\u2019Orves, 91120, Palaiseau, France","Linear Accelerator Laboratory, CNRS, Orsay, France","Inria, Parietal team, Palaiseau, France"],"affiliations":[{"raw_affiliation_string":"Inria, Parietal team, 1 Rue Honor\u00e9 d\u2019Estienne d\u2019Orves, 91120, Palaiseau, France","institution_ids":[]},{"raw_affiliation_string":"Linear Accelerator Laboratory, CNRS, Orsay, France","institution_ids":["https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Inria, Parietal team, Palaiseau, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074733625","display_name":"Ga\u00ebl Varoquaux","orcid":"https://orcid.org/0000-0003-1076-5122"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ga\u00ebl Varoquaux","raw_affiliation_strings":["Inria, Parietal team, 1 Rue Honor\u00e9 d\u2019Estienne d\u2019Orves, 91120, Palaiseau, France","Linear Accelerator Laboratory, CNRS, Orsay, France","Inria, Parietal team, Palaiseau, France"],"affiliations":[{"raw_affiliation_string":"Inria, Parietal team, 1 Rue Honor\u00e9 d\u2019Estienne d\u2019Orves, 91120, Palaiseau, France","institution_ids":[]},{"raw_affiliation_string":"Linear Accelerator Laboratory, CNRS, Orsay, France","institution_ids":["https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Inria, Parietal team, Palaiseau, France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051459492","display_name":"Bal\u00e1zs K\u00e9gl","orcid":"https://orcid.org/0000-0001-5610-1060"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Bal\u00e1zs K\u00e9gl","raw_affiliation_strings":["Inria, Parietal team, 1 Rue Honor\u00e9 d\u2019Estienne d\u2019Orves, 91120, Palaiseau, France","Linear Accelerator Laboratory, CNRS, Orsay, France","LAL, CNRS"],"affiliations":[{"raw_affiliation_string":"Inria, Parietal team, 1 Rue Honor\u00e9 d\u2019Estienne d\u2019Orves, 91120, Palaiseau, France","institution_ids":[]},{"raw_affiliation_string":"Linear Accelerator Laboratory, CNRS, Orsay, France","institution_ids":["https://openalex.org/I1294671590"]},{"raw_affiliation_string":"LAL, CNRS","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015283389"],"corresponding_institution_ids":["https://openalex.org/I1294671590"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":0.8462,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.80145701,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"107","issue":"8-10","first_page":"1477","last_page":"1494"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9987000226974487,"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/T11719","display_name":"Data Quality and Management","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.727558434009552},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6742574572563171},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.6369743347167969},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6363639235496521},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6290416121482849},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5186663866043091},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4865044951438904},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.4655305743217468},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.4556799530982971},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.44808757305145264},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4259631633758545},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4222589433193207},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3840486407279968},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36818403005599976},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2780620753765106}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.727558434009552},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6742574572563171},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.6369743347167969},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6363639235496521},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6290416121482849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5186663866043091},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4865044951438904},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.4655305743217468},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.4556799530982971},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.44808757305145264},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4259631633758545},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4222589433193207},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3840486407279968},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36818403005599976},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2780620753765106},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1007/s10994-018-5724-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-018-5724-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-018-5724-2.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1806.00979","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.00979","pdf_url":"https://arxiv.org/pdf/1806.00979","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":"mag:2805979482","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1806.00979","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:HAL:hal-01806175v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-01806175","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":"Machine Learning, 2018, ⟨10.1007/s10994-018-5724-2⟩","raw_type":"Journal articles"},{"id":"doi:10.48550/arxiv.1806.00979","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1806.00979","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s10994-018-5724-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-018-5724-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-018-5724-2.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G232567176","display_name":null,"funder_award_id":"ANR-17-CE23-0018","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G6803667113","display_name":null,"funder_award_id":"ANR-17","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G8629753466","display_name":null,"funder_award_id":"ANR-17-CE23-001","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2805979482.pdf","grobid_xml":"https://content.openalex.org/works/W2805979482.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W509898","https://openalex.org/W26591655","https://openalex.org/W46452414","https://openalex.org/W1452874900","https://openalex.org/W1491317234","https://openalex.org/W1502624642","https://openalex.org/W1530010412","https://openalex.org/W1556996173","https://openalex.org/W1610496399","https://openalex.org/W1614298861","https://openalex.org/W1647671624","https://openalex.org/W1971285215","https://openalex.org/W1990836268","https://openalex.org/W2001759055","https://openalex.org/W2031250218","https://openalex.org/W2034190452","https://openalex.org/W2038281398","https://openalex.org/W2043610825","https://openalex.org/W2066102695","https://openalex.org/W2067566391","https://openalex.org/W2070996757","https://openalex.org/W2073471108","https://openalex.org/W2079451707","https://openalex.org/W2101234009","https://openalex.org/W2115822498","https://openalex.org/W2135579862","https://openalex.org/W2158747611","https://openalex.org/W2158997610","https://openalex.org/W2163993443","https://openalex.org/W2171313960","https://openalex.org/W2185019360","https://openalex.org/W2427606719","https://openalex.org/W2464785945","https://openalex.org/W2548122763","https://openalex.org/W2767280887","https://openalex.org/W2950577311","https://openalex.org/W2952566282","https://openalex.org/W3146259567","https://openalex.org/W4239677523","https://openalex.org/W4285719527","https://openalex.org/W4297944350","https://openalex.org/W6601052559","https://openalex.org/W6604605561","https://openalex.org/W6629596221","https://openalex.org/W6633667658","https://openalex.org/W6636177537","https://openalex.org/W6675354045","https://openalex.org/W6681302627"],"related_works":["https://openalex.org/W2023703869","https://openalex.org/W2138437702","https://openalex.org/W1588091815","https://openalex.org/W2139945125","https://openalex.org/W2093270024","https://openalex.org/W2004134257","https://openalex.org/W3021272084","https://openalex.org/W2552728110","https://openalex.org/W2971101812","https://openalex.org/W3029855794","https://openalex.org/W2141536962","https://openalex.org/W1532499126","https://openalex.org/W1892813713","https://openalex.org/W2591621978","https://openalex.org/W2017753937","https://openalex.org/W2159261254","https://openalex.org/W2096692384","https://openalex.org/W1988041031","https://openalex.org/W1985463782","https://openalex.org/W2989787960"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}