{"id":"https://openalex.org/W1485084946","doi":"https://doi.org/10.1109/icde.2015.7113356","title":"Groupwise analytics via adaptive MapReduce","display_name":"Groupwise analytics via adaptive MapReduce","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1485084946","doi":"https://doi.org/10.1109/icde.2015.7113356","mag":"1485084946"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2015.7113356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2015.7113356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 31st International Conference on Data Engineering","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/A5112390564","display_name":"Liping Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]},{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Liping Peng","raw_affiliation_strings":["IBM Almaden Research Center","School of Computer Science, University of Massachusetts, Amherst"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"School of Computer Science, University of Massachusetts, Amherst","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065055611","display_name":"Vuk Ercegovac","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vuk Ercegovac","raw_affiliation_strings":["Computer Science Department, University of California, Berkeley","IBM Almaden Research Center"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"IBM Almaden Research Center","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032503782","display_name":"Kai Zeng","orcid":"https://orcid.org/0009-0005-5788-5668"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Zeng","raw_affiliation_strings":["IBM Almaden Research Center","Platfora, Inc"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"Platfora, Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090729930","display_name":"Peter J. Haas","orcid":"https://orcid.org/0000-0001-5694-3065"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter J. Haas","raw_affiliation_strings":["Google, Inc","IBM Almaden Research Center"],"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"IBM Almaden Research Center","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003379355","display_name":"Andrey Balmin","orcid":"https://orcid.org/0000-0003-3034-6259"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrey Balmin","raw_affiliation_strings":["IBM Research, Almaden"],"affiliations":[{"raw_affiliation_string":"IBM Research, Almaden","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048704801","display_name":"Yannis Sismanis","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yannis Sismanis","raw_affiliation_strings":["Google, Inc","IBM Almaden Research Center"],"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"IBM Almaden Research Center","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5112390564"],"corresponding_institution_ids":["https://openalex.org/I24603500","https://openalex.org/I4210085935"],"apc_list":null,"apc_paid":null,"fwci":0.3328,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62318425,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"4","issue":null,"first_page":"1059","last_page":"1070"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10799","display_name":"Data Visualization and Analytics","score":0.9965999722480774,"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/computer-science","display_name":"Computer science","score":0.8115167617797852},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.6562773585319519},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3797352612018585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8115167617797852},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.6562773585319519},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3797352612018585}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icde.2015.7113356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2015.7113356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 31st International Conference on Data Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W135476618","https://openalex.org/W1979819093","https://openalex.org/W1986517320","https://openalex.org/W2001183701","https://openalex.org/W2022858489","https://openalex.org/W2028226582","https://openalex.org/W2029948740","https://openalex.org/W2037701287","https://openalex.org/W2043097023","https://openalex.org/W2083541728","https://openalex.org/W2083966857","https://openalex.org/W2090452820","https://openalex.org/W2119885577","https://openalex.org/W2122465391","https://openalex.org/W2123577276","https://openalex.org/W2131975293","https://openalex.org/W2146620757","https://openalex.org/W2152029707","https://openalex.org/W2156632255","https://openalex.org/W2164507334","https://openalex.org/W2296677182","https://openalex.org/W2329095262","https://openalex.org/W2504767107","https://openalex.org/W6679815717","https://openalex.org/W6684060480"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W4390482427"],"abstract_inverted_index":{"Shared-nothing":[0],"systems":[1,20,250],"such":[2,214],"as":[3,127,215],"Hadoop":[4,187,216],"vastly":[5],"simplify":[6],"parallel":[7],"programming":[8],"when":[9],"processing":[10],"disk-resident":[11,252],"data":[12,40,99,181,202],"whose":[13],"size":[14],"exceeds":[15],"aggregate":[16],"cluster":[17],"memory.":[18],"Such":[19],"incur":[21],"a":[22,48,105,131,178,212],"significant":[23],"performance":[24],"penalty,":[25],"however,":[26],"on":[27,185],"the":[28,39,58,98,109,115,118,136,144,152,169,186,191,201,209],"important":[29],"class":[30],"of":[31,57,62,74,97,135,151,195,208,211,229,235],"\u201cgroupwise":[32],"set-valued":[33,49],"analytics\u201d":[34],"(GSVA)":[35],"queries":[36,76,93,165],"in":[37,104,138],"which":[38],"is":[41,51,128,155],"dynamically":[42],"partitioned":[43],"into":[44],"groups":[45],"and":[46,69,84,112,189,223],"then":[47,113],"synopsis":[50,116],"computed":[52],"for":[53,81,117,226],"some":[54],"or":[55],"all":[56,96,102],"groups.":[59],"Key":[60],"examples":[61],"synopses":[63],"include":[64,77],"top-k":[65],"sets,":[66,68],"bottom-k":[67],"uniform":[70],"random":[71],"samples.":[72],"Applications":[73],"GSVA":[75,92,164,220],"micro-marketing,":[78],"root-cause":[79],"analysis":[80],"problem":[82],"diagnosis,":[83],"fraud":[85],"detection.":[86],"A":[87],"naive":[88],"approach":[89,121,205],"to":[90,143,160,172,175,199,237,247],"executing":[91],"first":[94],"reshuffles":[95],"so":[100,148],"that":[101,149],"records":[103,137],"group":[106,140],"are":[107],"at":[108],"same":[110],"node":[111],"computes":[114],"group.":[119],"This":[120],"can":[122,243],"be":[123,245],"extremely":[124],"inefficient":[125],"when,":[126],"typical,":[129],"only":[130],"very":[132],"small":[133],"fraction":[134],"each":[139],"actually":[141],"contribute":[142],"final":[145],"groupwise":[146],"synopsis,":[147],"most":[150,207],"shuffling":[153],"effort":[154],"wasted.":[156],"We":[157],"show":[158,233],"how":[159],"significantly":[161,218],"speed":[162],"up":[163,236],"by":[166],"slightly":[167],"modifying":[168],"shared-nothing":[170,249],"environment":[171],"allow":[173],"tasks":[174],"occasionally":[176],"access":[177],"small,":[179],"common":[180],"structure;":[182],"we":[183],"focus":[184],"setting":[188],"use":[190],"\u201cAdaptive":[192],"MapReduce\u201d":[193],"infrastructure":[194],"Vernica":[196],"et":[197],"al.":[198],"implement":[200],"structure.":[203],"Our":[204],"retains":[206],"advantages":[210],"system":[213],"while":[217],"improving":[219],"query":[221,230],"performance,":[222],"also":[224],"allows":[225],"incremental":[227],"updating":[228],"results.":[231],"Experiments":[232],"speedups":[234],"5x.":[238],"Importantly,":[239],"our":[240],"new":[241],"technique":[242],"potentially":[244],"applied":[246],"other":[248],"with":[251],"data.":[253]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}