{"id":"https://openalex.org/W2991297706","doi":"https://doi.org/10.1007/s10618-021-00791-3","title":"Matrix sketching for supervised classification with imbalanced classes","display_name":"Matrix sketching for supervised classification with imbalanced classes","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W2991297706","doi":"https://doi.org/10.1007/s10618-021-00791-3","mag":"2991297706"},"language":"en","primary_location":{"id":"doi:10.1007/s10618-021-00791-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-021-00791-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-021-00791-3.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining and Knowledge Discovery","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10618-021-00791-3.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015901164","display_name":"Roberta Falcone","orcid":null},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Roberta Falcone","raw_affiliation_strings":["Department of Statistical Sciences, University of Bologna, Bologna, Italy","University of Bologna"],"affiliations":[{"raw_affiliation_string":"Department of Statistical Sciences, University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]},{"raw_affiliation_string":"University of Bologna","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060308577","display_name":"Laura Anderlucci","orcid":"https://orcid.org/0000-0003-1161-6145"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Laura Anderlucci","raw_affiliation_strings":["Department of Statistical Sciences, University of Bologna, Bologna, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Statistical Sciences, University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040194119","display_name":"Angela Montanari","orcid":"https://orcid.org/0000-0002-8369-1761"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Angela Montanari","raw_affiliation_strings":["Department of Statistical Sciences, University of Bologna, Bologna, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Statistical Sciences, University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015901164"],"corresponding_institution_ids":["https://openalex.org/I9360294"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.00413324,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"36","issue":"1","first_page":"174","last_page":"208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9997000098228455,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9997000098228455,"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":0.9944000244140625,"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":0.9941999912261963,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.6578482389450073},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6365483999252319},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6237690448760986},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.567791759967804},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45966801047325134},{"id":"https://openalex.org/keywords/design-matrix","display_name":"Design matrix","score":0.455073744058609},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.44509539008140564},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4195694625377655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4093875288963318},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33551880717277527},{"id":"https://openalex.org/keywords/linear-regression","display_name":"Linear regression","score":0.2514902353286743}],"concepts":[{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.6578482389450073},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6365483999252319},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6237690448760986},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.567791759967804},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45966801047325134},{"id":"https://openalex.org/C203233044","wikidata":"https://www.wikidata.org/wiki/Q5264358","display_name":"Design matrix","level":3,"score":0.455073744058609},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44509539008140564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4195694625377655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4093875288963318},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33551880717277527},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.2514902353286743},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s10618-021-00791-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-021-00791-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-021-00791-3.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining and Knowledge Discovery","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1912.00905","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.00905","pdf_url":"https://arxiv.org/pdf/1912.00905","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":"","raw_type":"text"},{"id":"mag:2991297706","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1912.00905","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.1912.00905","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1912.00905","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/s10618-021-00791-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-021-00791-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-021-00791-3.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining and Knowledge Discovery","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"No poverty","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/1"}],"awards":[{"id":"https://openalex.org/G6668775143","display_name":null,"funder_award_id":"FA9550-17-1-010","funder_id":"https://openalex.org/F4320332467","funder_display_name":"U.S. Air Force"}],"funders":[{"id":"https://openalex.org/F4320332467","display_name":"U.S. Air Force","ror":"https://ror.org/006gmme17"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2991297706.pdf","grobid_xml":"https://content.openalex.org/works/W2991297706.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W122912556","https://openalex.org/W373407302","https://openalex.org/W1964089535","https://openalex.org/W1970957555","https://openalex.org/W1976896995","https://openalex.org/W1988056000","https://openalex.org/W2000031724","https://openalex.org/W2001619934","https://openalex.org/W2011376672","https://openalex.org/W2020144485","https://openalex.org/W2053724458","https://openalex.org/W2058732827","https://openalex.org/W2063698478","https://openalex.org/W2065330407","https://openalex.org/W2087691922","https://openalex.org/W2093813380","https://openalex.org/W2094947835","https://openalex.org/W2105180131","https://openalex.org/W2117190680","https://openalex.org/W2125055259","https://openalex.org/W2129476886","https://openalex.org/W2142713577","https://openalex.org/W2148143831","https://openalex.org/W2157988812","https://openalex.org/W2164296439","https://openalex.org/W2297432279","https://openalex.org/W2318908986","https://openalex.org/W2338318698","https://openalex.org/W2490420619","https://openalex.org/W2538183362","https://openalex.org/W2562319768","https://openalex.org/W2580753685","https://openalex.org/W2589805776","https://openalex.org/W2593875029","https://openalex.org/W2625592596","https://openalex.org/W2765177294","https://openalex.org/W2807873700","https://openalex.org/W2979473749","https://openalex.org/W2981515171","https://openalex.org/W3046870591","https://openalex.org/W3048071527","https://openalex.org/W3098488568","https://openalex.org/W3112410551","https://openalex.org/W3120740533","https://openalex.org/W3155649056","https://openalex.org/W4229706427","https://openalex.org/W4252625959"],"related_works":["https://openalex.org/W3048071527","https://openalex.org/W2811451157","https://openalex.org/W2760834907","https://openalex.org/W2263105607","https://openalex.org/W3169478369","https://openalex.org/W2824314963","https://openalex.org/W3170938791","https://openalex.org/W2147876569","https://openalex.org/W3168767106","https://openalex.org/W2123432850","https://openalex.org/W3098277223","https://openalex.org/W2065218422","https://openalex.org/W2154959474","https://openalex.org/W2049488676","https://openalex.org/W2246823984","https://openalex.org/W2749962142","https://openalex.org/W2405274037","https://openalex.org/W2585649082","https://openalex.org/W2771262929","https://openalex.org/W2075654122"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"presence":[2],"of":[3,79,82,130,165],"imbalanced":[4],"classes":[5],"is":[6,16,66,74,87,94],"more":[7,9],"and":[8,14,101,178,185],"common":[10],"in":[11,37,89],"practical":[12],"applications":[13],"it":[15],"known":[17],"to":[18,48,53,103,134,141,197],"heavily":[19],"compromise":[20],"the":[21,42,77,83,90,97,125,142,152,158,163,198],"learning":[22],"process.":[23],"In":[24],"this":[25,35,55],"paper":[26],"we":[27],"propose":[28,133],"a":[29,50,67,110,194],"new":[30],"method":[31,167],"aimed":[32],"at":[33],"addressing":[34],"issue":[36],"binary":[38],"supervised":[39],"classification.":[40],"Re-balancing":[41],"class":[43,154],"sizes":[44],"has":[45],"turned":[46],"out":[47],"be":[49],"fruitful":[51],"strategy":[52],"overcome":[54],"problem.":[56],"Our":[57],"proposal":[58],"performs":[59],"re-balancing":[60,144],"through":[61],"matrix":[62,136],"sketching.":[63],"Matrix":[64],"sketching":[65,137,191],"recently":[68],"developed":[69],"data":[70],"compression":[71],"technique":[72],"that":[73,86,146,190],"characterized":[75],"by":[76,96],"property":[78,93],"preserving":[80],"most":[81,199],"linear":[84,171],"information":[85],"present":[88],"data.":[91,187],"Such":[92],"guaranteed":[95],"Johnson-Lindenstrauss\u2019":[98],"Lemma":[99],"(1984)":[100],"allows":[102],"embed":[104],"an":[105,116,139],"n":[106],"-dimensional":[107],"space":[108],"into":[109],"reduced":[111],"one":[112],"without":[113],"distorting,":[114],"within":[115],"$$\\epsilon":[117],"$$":[118],"<mml:math":[119],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\">":[120],"<mml:mi>\u03f5</mml:mi>":[121],"</mml:math>":[122],"-size":[123],"interval,":[124],"distances":[126],"between":[127],"any":[128],"pair":[129],"points.":[131],"We":[132,161],"use":[135],"as":[138],"alternative":[140,196],"standard":[143],"strategies":[145],"are":[147],"based":[148],"on":[149,183],"random":[150,156],"under-sampling":[151],"majority":[153],"or":[155],"over-sampling":[157],"minority":[159],"one.":[160],"assess":[162],"properties":[164],"our":[166],"when":[168],"combined":[169],"with":[170],"discriminant":[172],"analysis":[173],"(LDA),":[174],"classification":[175],"trees":[176],"(C4.5)":[177],"Support":[179],"Vector":[180],"Machines":[181],"(SVM)":[182],"simulated":[184],"real":[186],"Results":[188],"show":[189],"can":[192],"represent":[193],"sound":[195],"widely":[200],"used":[201],"rebalancing":[202],"methods.":[203]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}