{"id":"https://openalex.org/W4406458165","doi":"https://doi.org/10.1109/bigdata62323.2024.10825803","title":"A Hybrid Approach to Group-By and Aggregation Query Execution","display_name":"A Hybrid Approach to Group-By and Aggregation Query Execution","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406458165","doi":"https://doi.org/10.1109/bigdata62323.2024.10825803"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5114761212","display_name":"Gaurav Vaghasiya","orcid":null},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gaurav Vaghasiya","raw_affiliation_strings":["Santa Clara University,Santa Clara,CA"],"affiliations":[{"raw_affiliation_string":"Santa Clara University,Santa Clara,CA","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056183028","display_name":"Shiva Jahangiri","orcid":"https://orcid.org/0009-0001-4854-0597"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiva Jahangiri","raw_affiliation_strings":["Santa Clara University,Santa Clara,CA"],"affiliations":[{"raw_affiliation_string":"Santa Clara University,Santa Clara,CA","institution_ids":["https://openalex.org/I16269868"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5114761212"],"corresponding_institution_ids":["https://openalex.org/I16269868"],"apc_list":null,"apc_paid":null,"fwci":0.3564,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66096202,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3799","last_page":"3808"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9993000030517578,"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":0.9993000030517578,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9973999857902527,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7758594751358032},{"id":"https://openalex.org/keywords/group","display_name":"Group (periodic table)","score":0.5798658132553101},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.4962676167488098},{"id":"https://openalex.org/keywords/rdf-query-language","display_name":"RDF query language","score":0.4185086786746979},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.34661388397216797},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33349770307540894},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.27673715353012085},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.19381630420684814},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.15191856026649475},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.07334449887275696}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7758594751358032},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.5798658132553101},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.4962676167488098},{"id":"https://openalex.org/C96956885","wikidata":"https://www.wikidata.org/wiki/Q6138701","display_name":"RDF query language","level":5,"score":0.4185086786746979},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.34661388397216797},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33349770307540894},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.27673715353012085},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.19381630420684814},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.15191856026649475},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.07334449887275696},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W141912388","https://openalex.org/W1501284171","https://openalex.org/W1974796034","https://openalex.org/W2020191321","https://openalex.org/W2020272913","https://openalex.org/W2063259549","https://openalex.org/W2067089961","https://openalex.org/W2098372784","https://openalex.org/W2116436709","https://openalex.org/W2130911657","https://openalex.org/W2158237121","https://openalex.org/W2169486917","https://openalex.org/W2210479044","https://openalex.org/W2221398285","https://openalex.org/W2265297126","https://openalex.org/W2406955896","https://openalex.org/W2595024241","https://openalex.org/W3008676651","https://openalex.org/W3174401400","https://openalex.org/W4308883303","https://openalex.org/W6629161310","https://openalex.org/W6629717275","https://openalex.org/W6632064309","https://openalex.org/W6760040044"],"related_works":["https://openalex.org/W1574546694","https://openalex.org/W2401447141","https://openalex.org/W2096359267","https://openalex.org/W4240472508","https://openalex.org/W2394844208","https://openalex.org/W2556786504","https://openalex.org/W3125756434","https://openalex.org/W2614542053","https://openalex.org/W2538384344","https://openalex.org/W2353434938"],"abstract_inverted_index":{"Group-By-Aggregate":[0],"(GBA)":[1],"queries":[2,36,253],"are":[3,63,76,83,159],"fundamental":[4],"in":[5,53,254],"data":[6,12,93,128,162,256],"analysis,":[7],"allowing":[8],"users":[9],"to":[10,26,66,121,175],"organize":[11],"by":[13],"specific":[14],"attributes":[15],"and":[16,24,47,85,95,108,137,164,168,179,183,206,232,246],"apply":[17],"aggregate":[18],"functions,":[19],"such":[20],"as":[21],"sum,":[22],"average,":[23],"count,":[25],"generate":[27],"insights":[28],"from":[29,88],"large":[30],"datasets.":[31],"Traditionally,":[32],"DBMSs":[33],"handle":[34],"GBA":[35,110,132,181,239,252],"through":[37],"either":[38],"sort-based":[39,145],"or":[40,189,224],"hashbased":[41],"methods,":[42],"each":[43,226],"with":[44,78,144],"unique":[45],"strengths":[46,120],"limitations.":[48],"Sortbased":[49],"approaches,":[50],"while":[51],"effective":[52],"certain":[54],"contexts,":[55],"can":[56],"become":[57],"computationally":[58],"expensive":[59],"when":[60,156],"few":[61],"groups":[62],"involved":[64],"due":[65],"extensive":[67],"record":[68],"comparisons.":[69],"On":[70],"the":[71,141,148,173,193,212,217,220],"other":[72],"hand,":[73],"hash-based":[74,109,135],"methods":[75],"efficient":[77,248],"larger":[79],"group":[80],"counts":[81],"but":[82],"memoryintensive":[84],"may":[86],"suffer":[87],"hash":[89,180],"collisions,":[90],"depending":[91],"on":[92,105,186,203],"distribution":[94],"hashing":[96],"functions.This":[97],"paper":[98],"presents":[99],"an":[100],"empirical":[101],"performance":[102,125,218],"study":[103],"focused":[104],"traditional":[106],"sort-":[107],"operators,":[111],"introducing":[112],"a":[113,242],"robust":[114],"hybrid":[115,131,194,213],"approach":[116,214],"that":[117,211],"unifies":[118],"their":[119],"deliver":[122],"consistent,":[123],"high":[124],"across":[126,228],"diverse":[127],"conditions.":[129],"The":[130],"method":[133,195,249],"combines":[134],"grouping":[136],"early":[138],"aggregation":[139,146],"for":[140,147,250],"local":[142],"phase":[143],"global":[149],"phase.":[150],"It":[151],"forwards":[152],"partially":[153],"aggregated":[154],"results":[155],"memory":[157,166],"limits":[158],"reached,":[160],"reducing":[161],"volume":[163],"minimizing":[165],"usage":[167],"disk":[169],"I/O.":[170],"By":[171],"eliminating":[172],"need":[174],"choose":[176],"between":[177],"sort":[178,223],"operators":[182],"removing":[184],"dependency":[185],"precise":[187],"statistics":[188],"query":[190,198],"optimizer":[191],"intervention,":[192],"significantly":[196],"enhances":[197],"execution":[199],"reliability.":[200],"Extensive":[201],"testing":[202],"Wisconsin,":[204],"TPC-H,":[205],"TPC-DS":[207],"benchmark":[208],"datasets":[209],"demonstrates":[210],"consistently":[215],"matches":[216],"of":[219],"bestsuited":[221],"algorithm\u2014whether":[222],"hash\u2014in":[225],"scenario,":[227],"varying":[229],"dataset":[230],"sizes":[231],"complexities.":[233],"This":[234],"unified":[235],"solution":[236],"replaces":[237],"separate":[238],"algorithms,":[240],"providing":[241],"flexible,":[243],"easily":[244],"adaptable,":[245],"highly":[247],"processing":[251],"big":[255],"management":[257],"systems.":[258]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}