{"id":"https://openalex.org/W3007568659","doi":"https://doi.org/10.1109/bigdata47090.2019.9006448","title":"Sparse Block Regression (SBR) for Big Data with Categorical Variables","display_name":"Sparse Block Regression (SBR) for Big Data with Categorical Variables","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007568659","doi":"https://doi.org/10.1109/bigdata47090.2019.9006448","mag":"3007568659"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata47090.2019.9006448","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006448","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100668156","display_name":"Xiang Liu","orcid":"https://orcid.org/0000-0002-4874-4071"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiang Liu","raw_affiliation_strings":["Purdue University, West Lafayette, Indiana"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, Indiana","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066571491","display_name":"Huyunting Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huyunting Huang","raw_affiliation_strings":["Purdue University, West Lafayette, Indiana"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, Indiana","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074605808","display_name":"Ziyang Tang","orcid":"https://orcid.org/0000-0002-0019-7988"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziyang Tang","raw_affiliation_strings":["Purdue University, West Lafayette, Indiana"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, Indiana","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089567067","display_name":"Tonglin Zhang","orcid":"https://orcid.org/0000-0003-3312-2293"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tonglin Zhang","raw_affiliation_strings":["Purdue University, West Lafayette, Indiana"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, Indiana","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089355143","display_name":"Baijian Yang","orcid":"https://orcid.org/0000-0003-4440-3701"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baijian Yang","raw_affiliation_strings":["Purdue University, West Lafayette, Indiana"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, Indiana","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2034,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57223613,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":95},"biblio":{"volume":"9","issue":null,"first_page":"221","last_page":"226"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9987999796867371,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.9183777570724487},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6445212364196777},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5464056134223938},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5324182510375977},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5186528563499451},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.5042134523391724},{"id":"https://openalex.org/keywords/workaround","display_name":"Workaround","score":0.48168620467185974},{"id":"https://openalex.org/keywords/design-matrix","display_name":"Design matrix","score":0.456666499376297},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.42026591300964355},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41557157039642334},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.38431015610694885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3829893469810486},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3551281690597534},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.310305655002594},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23521649837493896},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.20689043402671814}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.9183777570724487},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6445212364196777},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5464056134223938},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5324182510375977},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5186528563499451},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.5042134523391724},{"id":"https://openalex.org/C194541083","wikidata":"https://www.wikidata.org/wiki/Q457174","display_name":"Workaround","level":2,"score":0.48168620467185974},{"id":"https://openalex.org/C203233044","wikidata":"https://www.wikidata.org/wiki/Q5264358","display_name":"Design matrix","level":3,"score":0.456666499376297},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.42026591300964355},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41557157039642334},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.38431015610694885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3829893469810486},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3551281690597534},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.310305655002594},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23521649837493896},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.20689043402671814},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata47090.2019.9006448","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006448","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W1506342804","https://openalex.org/W2054594459","https://openalex.org/W2072336782","https://openalex.org/W2118585731","https://openalex.org/W2146241755","https://openalex.org/W2153820245","https://openalex.org/W2163614729","https://openalex.org/W2220584184","https://openalex.org/W2403026333","https://openalex.org/W2520570087","https://openalex.org/W2548570154","https://openalex.org/W2567092460","https://openalex.org/W2611165208","https://openalex.org/W2791047467","https://openalex.org/W3006860201","https://openalex.org/W4285719527","https://openalex.org/W4292081093","https://openalex.org/W4297957988","https://openalex.org/W6677656871","https://openalex.org/W6683915439"],"related_works":["https://openalex.org/W4381612620","https://openalex.org/W2950380533","https://openalex.org/W2998499456","https://openalex.org/W2893207040","https://openalex.org/W3127868735","https://openalex.org/W1840516357","https://openalex.org/W2753986652","https://openalex.org/W4387616455","https://openalex.org/W971576836","https://openalex.org/W4390437797"],"abstract_inverted_index":{"Categorical":[0],"variables":[1,4,14],"are":[2,118],"nominal":[3],"that":[5,76,231],"classify":[6],"observations":[7],"by":[8,190],"groups.":[9],"The":[10,94,176,218,228],"treatment":[11],"of":[12,43,92,132,138,148,202],"categorical":[13,39,86,128],"in":[15,60,140,205,255],"regression":[16,161,239],"is":[17,72,97],"a":[18,30,38,61,67,85,89,127,169,199],"well-studied":[19],"yet":[20],"vital":[21],"problem,":[22],"with":[23,198,214,241],"the":[24,48,52,56,98,110,136,185,206,212,238,247,258],"most":[25],"popular":[26],"solution":[27],"to":[28,74,108,122,163,246],"perform":[29],"one":[31,77,191],"hot":[32,78,192],"encoding.":[33],"However,":[34,113],"challenges":[35],"arise":[36],"if":[37],"variable":[40,87,129],"has":[41,81,88,130],"millions":[42,131],"levels.":[44,93,133],"It":[45],"will":[46],"cause":[47],"memory":[49,59,186,254],"needed":[50],"for":[51],"computation":[53],"far":[54],"exceeds":[55,146],"total":[57],"available":[58],"given":[62],"computer":[63,68],"system":[64],"or":[65],"even":[66],"cluster.":[69],"Thus,":[70],"it":[71,103],"fair":[73],"state":[75],"encoding":[79],"approach":[80,101,157],"its":[82],"limitations":[83],"when":[84,126],"large":[90,242],"number":[91,137],"common":[95],"workaround":[96],"sparse":[99,115,159,170,225,248],"matrix":[100,116,172,216,226,249],"because":[102],"requires":[104],"much":[105],"fewer":[106],"resources":[107],"cache":[109],"dummy":[111],"variables.":[112],"existing":[114],"approaches":[117],"still":[119],"not":[120,180],"sufficient":[121,174],"handle":[123],"extreme":[124],"cases":[125],"For":[134],"instance,":[135],"subnets":[139],"network":[141],"traffic":[142],"analyses":[143],"can":[144,233],"easily":[145],"tens":[147],"millions.":[149],"In":[150],"this":[151,165],"paper,":[152],"we":[153],"proposed":[154,221],"an":[155],"innovative":[156],"called":[158],"block":[160,171],"(SBR)":[162],"address":[164],"challenge.":[166],"SBR":[167,222,232,251],"constructs":[168],"using":[173],"statistics.":[175],"benefits":[177],"include":[178],"but":[179],"limited":[181],"to:":[182],"1)":[183],"overcome":[184],"barrier":[187],"issue":[188],"caused":[189],"encoding,":[193],"2)":[194],"obtain":[195],"multiple":[196],"models":[197,213],"single":[200],"scan":[201],"data":[203],"stored":[204],"secondary":[207],"storage;":[208],"and":[209,235],"3)":[210],"update":[211],"simple":[215],"operations.":[217],"study":[219],"compared":[220],"against":[223],"conventional":[224],"approaches.":[227],"experiments":[229],"proved":[230],"efficiently":[234],"accurately":[236],"solve":[237],"problem":[240],"category":[243],"number.":[244],"Compared":[245],"approach,":[250],"saved":[252],"90%":[253],"size":[256],"during":[257],"computation.":[259]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}