{"id":"https://openalex.org/W2911536067","doi":"https://doi.org/10.14778/3291264.3291273","title":"Chasing similarity","display_name":"Chasing similarity","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2911536067","doi":"https://doi.org/10.14778/3291264.3291273","mag":"2911536067"},"language":"en","primary_location":{"id":"doi:10.14778/3291264.3291273","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3291264.3291273","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5070153632","display_name":"Feilong Liu","orcid":"https://orcid.org/0000-0002-8638-2294"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feilong Liu","raw_affiliation_strings":["The Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058708399","display_name":"Ario Salmasi","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ario Salmasi","raw_affiliation_strings":["The Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001035930","display_name":"Spyros Blanas","orcid":"https://orcid.org/0009-0004-2703-7177"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Spyros Blanas","raw_affiliation_strings":["The Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013188587","display_name":"Anastasios Sidiropoulos","orcid":null},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anastasios Sidiropoulos","raw_affiliation_strings":["University of Illinois at Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5244,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.95489097,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"12","issue":"3","first_page":"292","last_page":"306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994000196456909,"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/T11106","display_name":"Data Management and Algorithms","score":0.9993000030517578,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9955999851226807,"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/grasp","display_name":"GRASP","score":0.7841694355010986},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7577901482582092},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.6717170476913452},{"id":"https://openalex.org/keywords/loom","display_name":"LOOM","score":0.6082807183265686},{"id":"https://openalex.org/keywords/data-aggregator","display_name":"Data aggregator","score":0.5390377044677734},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.502434253692627},{"id":"https://openalex.org/keywords/conjecture","display_name":"Conjecture","score":0.444207102060318},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3963542580604553},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3817274570465088},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.25558924674987793},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2304171323776245},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.20425879955291748},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19374597072601318},{"id":"https://openalex.org/keywords/wireless-sensor-network","display_name":"Wireless sensor network","score":0.18734803795814514},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1578351855278015},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.117276132106781}],"concepts":[{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.7841694355010986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7577901482582092},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.6717170476913452},{"id":"https://openalex.org/C2778584943","wikidata":"https://www.wikidata.org/wiki/Q6459541","display_name":"LOOM","level":2,"score":0.6082807183265686},{"id":"https://openalex.org/C82578977","wikidata":"https://www.wikidata.org/wiki/Q16773055","display_name":"Data aggregator","level":3,"score":0.5390377044677734},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.502434253692627},{"id":"https://openalex.org/C2780990831","wikidata":"https://www.wikidata.org/wiki/Q319141","display_name":"Conjecture","level":2,"score":0.444207102060318},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3963542580604553},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3817274570465088},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.25558924674987793},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2304171323776245},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.20425879955291748},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19374597072601318},{"id":"https://openalex.org/C24590314","wikidata":"https://www.wikidata.org/wiki/Q336038","display_name":"Wireless sensor network","level":2,"score":0.18734803795814514},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1578351855278015},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.117276132106781},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3291264.3291273","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3291264.3291273","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1497089183","https://openalex.org/W1502916507","https://openalex.org/W1529847426","https://openalex.org/W1536639265","https://openalex.org/W1597532222","https://openalex.org/W1965562201","https://openalex.org/W1967601791","https://openalex.org/W1971885140","https://openalex.org/W1991800036","https://openalex.org/W1993226606","https://openalex.org/W2019404063","https://openalex.org/W2024680396","https://openalex.org/W2029866183","https://openalex.org/W2037027334","https://openalex.org/W2045725603","https://openalex.org/W2067089961","https://openalex.org/W2074935284","https://openalex.org/W2086977914","https://openalex.org/W2101161250","https://openalex.org/W2102967864","https://openalex.org/W2103201239","https://openalex.org/W2110514750","https://openalex.org/W2111519186","https://openalex.org/W2114103324","https://openalex.org/W2122179278","https://openalex.org/W2124645273","https://openalex.org/W2130531694","https://openalex.org/W2143295630","https://openalex.org/W2144499729","https://openalex.org/W2147717514","https://openalex.org/W2153259545","https://openalex.org/W2155599998","https://openalex.org/W2156855109","https://openalex.org/W2157614013","https://openalex.org/W2158237121","https://openalex.org/W2162747054","https://openalex.org/W2167396179","https://openalex.org/W2210299188","https://openalex.org/W2294501066","https://openalex.org/W2435648513","https://openalex.org/W2583754181","https://openalex.org/W2616697817","https://openalex.org/W2618868084","https://openalex.org/W2755385361","https://openalex.org/W2789037937","https://openalex.org/W2893742429","https://openalex.org/W2949611765","https://openalex.org/W2950416404","https://openalex.org/W2963554098","https://openalex.org/W2963638209","https://openalex.org/W3098222317","https://openalex.org/W4289401659","https://openalex.org/W4297971002","https://openalex.org/W6738002306"],"related_works":["https://openalex.org/W569395298","https://openalex.org/W2367230280","https://openalex.org/W2387643047","https://openalex.org/W2363650331","https://openalex.org/W2383621684","https://openalex.org/W2391287690","https://openalex.org/W2047869714","https://openalex.org/W2363863410","https://openalex.org/W2045966173","https://openalex.org/W4252109987"],"abstract_inverted_index":{"Parallel":[0,24],"aggregation":[1,25,72,100,126,182],"is":[2,10,65,107,130],"a":[3,85,103,118],"ubiquitous":[4],"operation":[5],"in":[6,15,18,22,139,148,164],"data":[7,105,146,176],"analytics":[8],"that":[9,66,88,97,123,178],"expressed":[11],"as":[12,132],"GROUP":[13],"BY":[14],"SQL,":[16],"reduce":[17,143],"Hadoop,":[19],"or":[20],"segment":[21],"TensorFlow.":[23],"starts":[26],"with":[27],"an":[28],"optional":[29],"local":[30,43,61],"pre-aggregation":[31,44],"step":[32],"and":[33,185],"then":[34],"repartitions":[35],"the":[36,40,50,67,77,90,110,135,144,155],"intermediate":[37],"result":[38],"across":[39],"network.":[41,78],"While":[42],"works":[45],"well":[46],"for":[47,56,70],"low-cardinality":[48],"aggregations,":[49],"network":[51,157,169],"communication":[52],"cost":[53],"remains":[54],"significant":[55],"high-cardinality":[57,71],"aggregations":[58,163],"even":[59],"after":[60],"pre-aggregation.":[62],"The":[63,171],"problem":[64],"repartition-based":[68,181],"algorithm":[69],"does":[73],"not":[74],"fully":[75],"utilize":[76],"In":[79,151],"this":[80],"work,":[81],"we":[82],"first":[83],"formulate":[84],"mathematical":[86],"model":[87],"captures":[89],"performance":[91],"of":[92],"parallel":[93,125],"aggregation.":[94],"We":[95,115],"prove":[96],"finding":[98],"optimal":[99],"plans":[101],"from":[102],"known":[104],"distribution":[106],"NP-hard,":[108],"assuming":[109],"Small":[111],"Set":[112],"Expansion":[113],"conjecture.":[114],"propose":[116],"GRASP,":[117],"GReedy":[119],"Aggregation":[120],"Scheduling":[121],"Protocol":[122],"decomposes":[124],"into":[127,159],"phases.":[128,150],"GRASP":[129,153,179],"distribution-aware":[131],"it":[133],"aggregates":[134],"most":[136],"similar":[137],"partitions":[138],"each":[140,165],"phase":[141,166],"to":[142,167],"transmitted":[145],"size":[147],"subsequent":[149],"addition,":[152],"takes":[154],"available":[156],"bandwidth":[158],"account":[160],"when":[161],"scheduling":[162],"maximize":[168],"utilization.":[170],"experimental":[172],"evaluation":[173],"on":[174],"real":[175],"shows":[177],"outperforms":[180],"by":[183,187],"3.5x":[184],"LOOM":[186],"2.0x.":[188]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2019-02-21T00:00:00"}