{"id":"https://openalex.org/W3216661918","doi":"https://doi.org/10.1109/tkde.2021.3132373","title":"Dimensionality Reduction for Categorical Data","display_name":"Dimensionality Reduction for Categorical Data","publication_year":2021,"publication_date":"2021-12-03","ids":{"openalex":"https://openalex.org/W3216661918","doi":"https://doi.org/10.1109/tkde.2021.3132373","mag":"3216661918"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2021.3132373","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2021.3132373","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2112.00362","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077953904","display_name":"Debajyoti Bera","orcid":"https://orcid.org/0000-0002-1626-7514"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Debajyoti Bera","raw_affiliation_strings":["Department of Computer Science and Engineering, Indraprastha Institute of Information Technology (IIIT-Delhi), DL, India"],"raw_orcid":"https://orcid.org/0000-0002-1626-7514","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indraprastha Institute of Information Technology (IIIT-Delhi), DL, India","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031238051","display_name":"Rameshwar Pratap","orcid":"https://orcid.org/0000-0002-8824-6202"},"institutions":[{"id":"https://openalex.org/I9579091","display_name":"Indian Institute of Technology Mandi","ror":"https://ror.org/05r9r2f34","country_code":"IN","type":"education","lineage":["https://openalex.org/I9579091"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rameshwar Pratap","raw_affiliation_strings":["Indian Institute of Technology, Mandi, HP, India"],"raw_orcid":"https://orcid.org/0000-0002-8824-6202","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Mandi, HP, India","institution_ids":["https://openalex.org/I9579091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046530015","display_name":"Bhisham Dev Verma","orcid":"https://orcid.org/0000-0002-4319-1199"},"institutions":[{"id":"https://openalex.org/I9579091","display_name":"Indian Institute of Technology Mandi","ror":"https://ror.org/05r9r2f34","country_code":"IN","type":"education","lineage":["https://openalex.org/I9579091"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Bhisham Dev Verma","raw_affiliation_strings":["Indian Institute of Technology, Mandi, HP, India"],"raw_orcid":"https://orcid.org/0000-0002-4319-1199","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Mandi, HP, India","institution_ids":["https://openalex.org/I9579091"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.273,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64316003,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"35","issue":"4","first_page":"3658","last_page":"3671"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9958999752998352,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9958999752998352,"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/T10057","display_name":"Face and Expression Recognition","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9889000058174133,"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/categorical-variable","display_name":"Categorical variable","score":0.8306223154067993},{"id":"https://openalex.org/keywords/hamming-space","display_name":"Hamming space","score":0.646148681640625},{"id":"https://openalex.org/keywords/hamming-distance","display_name":"Hamming distance","score":0.6439889669418335},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.593690037727356},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.5932537913322449},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5579059720039368},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5094566941261292},{"id":"https://openalex.org/keywords/hamming-code","display_name":"Hamming code","score":0.5035068392753601},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43189021944999695},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.43105530738830566},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.41113004088401794},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4023212790489197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3652305006980896},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3435763716697693},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32190990447998047},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17317917943000793},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.1055932343006134}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.8306223154067993},{"id":"https://openalex.org/C2779494224","wikidata":"https://www.wikidata.org/wiki/Q5645799","display_name":"Hamming space","level":5,"score":0.646148681640625},{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.6439889669418335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.593690037727356},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.5932537913322449},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5579059720039368},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5094566941261292},{"id":"https://openalex.org/C73150493","wikidata":"https://www.wikidata.org/wiki/Q853922","display_name":"Hamming code","level":4,"score":0.5035068392753601},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43189021944999695},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.43105530738830566},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.41113004088401794},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4023212790489197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3652305006980896},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3435763716697693},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32190990447998047},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17317917943000793},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.1055932343006134},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C157125643","wikidata":"https://www.wikidata.org/wiki/Q884707","display_name":"Block code","level":3,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tkde.2021.3132373","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2021.3132373","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:2112.00362","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.00362","pdf_url":"https://arxiv.org/pdf/2112.00362","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:3216661918","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2112.00362","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":"doi:10.48550/arxiv.2112.00362","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2112.00362","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-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2112.00362","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.00362","pdf_url":"https://arxiv.org/pdf/2112.00362","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":71,"referenced_works":["https://openalex.org/W47137029","https://openalex.org/W65738273","https://openalex.org/W1124708747","https://openalex.org/W1493892051","https://openalex.org/W1502916507","https://openalex.org/W1587559447","https://openalex.org/W1595409123","https://openalex.org/W1880262756","https://openalex.org/W1922404199","https://openalex.org/W1945899805","https://openalex.org/W1951217842","https://openalex.org/W1959608418","https://openalex.org/W1979356656","https://openalex.org/W1985514943","https://openalex.org/W1991800036","https://openalex.org/W2001141328","https://openalex.org/W2012833704","https://openalex.org/W2037757210","https://openalex.org/W2041836310","https://openalex.org/W2045533739","https://openalex.org/W2052570068","https://openalex.org/W2060170830","https://openalex.org/W2060300932","https://openalex.org/W2061375390","https://openalex.org/W2070996757","https://openalex.org/W2080234606","https://openalex.org/W2084812512","https://openalex.org/W2087221762","https://openalex.org/W2101234009","https://openalex.org/W2102409316","https://openalex.org/W2103126020","https://openalex.org/W2105732805","https://openalex.org/W2109293916","https://openalex.org/W2112431023","https://openalex.org/W2114720696","https://openalex.org/W2126105096","https://openalex.org/W2128804044","https://openalex.org/W2135029798","https://openalex.org/W2147152072","https://openalex.org/W2147717514","https://openalex.org/W2149230623","https://openalex.org/W2152799677","https://openalex.org/W2154053567","https://openalex.org/W2166559705","https://openalex.org/W2187089797","https://openalex.org/W2538769922","https://openalex.org/W2802170901","https://openalex.org/W2893679365","https://openalex.org/W2899702797","https://openalex.org/W2950336271","https://openalex.org/W2963733740","https://openalex.org/W2969132644","https://openalex.org/W2969761511","https://openalex.org/W2979473749","https://openalex.org/W2989661724","https://openalex.org/W3003717980","https://openalex.org/W3003897323","https://openalex.org/W3011584860","https://openalex.org/W3020873385","https://openalex.org/W3120740533","https://openalex.org/W3143596294","https://openalex.org/W4237791300","https://openalex.org/W6601876578","https://openalex.org/W6629956336","https://openalex.org/W6640963894","https://openalex.org/W6675354045","https://openalex.org/W6675401909","https://openalex.org/W6676014314","https://openalex.org/W6680012447","https://openalex.org/W6682557032","https://openalex.org/W6774910988"],"related_works":[],"abstract_inverted_index":{"Categorical":[0],"attributes":[1,22,35],"are":[2,117,125,185,224],"those":[3],"that":[4,84,110,113,211],"can":[5,87,148],"take":[6],"a":[7,61,140,145],"discrete":[8,25,38],"set":[9],"of":[10,98,106,170,191,194,233],"values,":[11],"e.g.,":[12],"colours.":[13],"This":[14],"work":[15],"is":[16,166,168,213],"about":[17],"compressing":[18,31],"vectors":[19,32,39],"over":[20,33],"categorical":[21,34,63],"to":[23,36,57,68,144],"low-dimension":[24,37],"vectors.":[26],"The":[27,158],"current":[28],"hash-based":[29],"methods":[30],"do":[40],"not":[41],"provide":[42],"any":[43],"guarantee":[44],"on":[45,205],"the":[46,50,70,75,91,99,104,107,114,121,129,133,164,171,192,217,226,229],"Hamming":[47,72,122,134],"distances":[48,73],"between":[49],"compressed":[51],"representations.":[52],"Here":[53],"we":[54,111],"present":[55],"<monospace>FSketch</monospace>":[56,195,212],"create":[58],"sketches":[59,86,115,223],"for":[60,179,228],"sparse":[62,163],"data":[64,77,93,101,146,165],"and":[65,120,132,167,196,216,238],"an":[66,155],"estimator":[67],"estimate":[69],"pairwise":[71],"among":[74,225],"uncompressed":[76],"only":[78],"from":[79],"their":[80],"sketches.":[81],"We":[82,209],"claim":[83],"these":[85],"be":[88,149],"used":[89],"in":[90,96,154],"usual":[92],"mining":[94],"tasks":[95,232],"place":[97],"original":[100,172],"without":[102],"compromising":[103],"quality":[105],"task.":[108],"For":[109],"ensure":[112],"also":[116],"categorical,":[118],"sparse,":[119],"distance":[123,135],"estimates":[124],"reasonably":[126],"precise.":[127],"Both":[128],"sketch":[130,153],"construction":[131],"estimation":[136],"algorithms":[137,204],"require":[138],"just":[139],"single-pass;":[141],"furthermore,":[142],"changes":[143],"point":[147],"incorporated":[150],"into":[151],"its":[152,222],"efficient":[156],"manner.":[157],"compressibility":[159],"depends":[160],"upon":[161],"how":[162],"independent":[169],"dimension":[173],"\u2013":[174],"making":[175],"our":[176],"algorithm":[177],"attractive":[178],"many":[180],"real-life":[181],"scenarios.":[182],"Our":[183],"claims":[184],"backed":[186],"by":[187,198,220],"rigorous":[188],"theoretical":[189],"analysis":[190],"properties":[193],"supplemented":[197],"extensive":[199],"comparative":[200],"evaluations":[201],"with":[202],"related":[203],"some":[206],"real-world":[207],"datasets.":[208],"show":[210],"significantly":[214],"faster,":[215],"accuracy":[218],"obtained":[219],"using":[221],"top":[227],"standard":[230],"unsupervised":[231],"<inline-formula><tex-math":[234],"notation=\"LaTeX\">$\\mathrm{RMSE}$</tex-math></inline-formula>":[235],",":[236],"clustering":[237],"similarity":[239],"search.":[240]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}