{"id":"https://openalex.org/W2766504241","doi":"https://doi.org/10.14778/3151106.3151110","title":"Blockjoin","display_name":"Blockjoin","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2766504241","doi":"https://doi.org/10.14778/3151106.3151110","mag":"2766504241"},"language":"en","primary_location":{"id":"doi:10.14778/3151106.3151110","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3151106.3151110","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":true,"oa_status":"green","oa_url":"https://zenodo.org/record/3456653","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072690436","display_name":"Andreas Kunft","orcid":"https://orcid.org/0000-0001-7557-1703"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Kunft","raw_affiliation_strings":["Technische Universit\u00e4t Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Berlin","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002932353","display_name":"Asterios Katsifodimos","orcid":"https://orcid.org/0000-0002-6717-2945"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Asterios Katsifodimos","raw_affiliation_strings":["Delft University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090934117","display_name":"Sebastian Schelter","orcid":"https://orcid.org/0000-0003-4722-5840"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Schelter","raw_affiliation_strings":["Technische Universit\u00e4t Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Berlin","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002030730","display_name":"Tilmann Rabl","orcid":"https://orcid.org/0009-0009-3335-8045"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tilmann Rabl","raw_affiliation_strings":["Technische Universit\u00e4t Berlin and German Research Center for Artificial Intelligence (DFKI)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Berlin and German Research Center for Artificial Intelligence (DFKI)","institution_ids":["https://openalex.org/I33256026","https://openalex.org/I4577782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002413906","display_name":"Volker Markl","orcid":"https://orcid.org/0009-0009-0964-026X"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Volker Markl","raw_affiliation_strings":["Technische Universit\u00e4t Berlin and German Research Center for Artificial Intelligence (DFKI)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Berlin and German Research Center for Artificial Intelligence (DFKI)","institution_ids":["https://openalex.org/I33256026","https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9921,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.85260371,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"10","issue":"13","first_page":"2061","last_page":"2072"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9998000264167786,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9998000264167786,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9990000128746033,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.7616070508956909},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.6957003474235535},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.6607059836387634},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.5801485776901245},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5352597236633301},{"id":"https://openalex.org/keywords/shuffling","display_name":"Shuffling","score":0.5237414836883545},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.49930596351623535},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.46504345536231995},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4275680482387543},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.42040717601776123},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3222843408584595},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.27563419938087463},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10678574442863464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7616070508956909},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.6957003474235535},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.6607059836387634},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.5801485776901245},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5352597236633301},{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.5237414836883545},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.49930596351623535},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.46504345536231995},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4275680482387543},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.42040717601776123},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3222843408584595},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.27563419938087463},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10678574442863464},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/3151106.3151110","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3151106.3151110","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"},{"id":"pmh:oai:zenodo.org:3456653","is_oa":true,"landing_page_url":"https://zenodo.org/record/3456653","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:3456653","is_oa":true,"landing_page_url":"https://zenodo.org/record/3456653","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W410850256","https://openalex.org/W1485587488","https://openalex.org/W1538786304","https://openalex.org/W1570477871","https://openalex.org/W1947869163","https://openalex.org/W1970372442","https://openalex.org/W1993226606","https://openalex.org/W1993433750","https://openalex.org/W2003515726","https://openalex.org/W2005112390","https://openalex.org/W2014830756","https://openalex.org/W2017383881","https://openalex.org/W2032775418","https://openalex.org/W2037168816","https://openalex.org/W2058178853","https://openalex.org/W2061601738","https://openalex.org/W2064366207","https://openalex.org/W2064619860","https://openalex.org/W2075620950","https://openalex.org/W2078945459","https://openalex.org/W2083036673","https://openalex.org/W2099102906","https://openalex.org/W2102458936","https://openalex.org/W2111708605","https://openalex.org/W2116926680","https://openalex.org/W2143108641","https://openalex.org/W2146183750","https://openalex.org/W2146635036","https://openalex.org/W2167927436","https://openalex.org/W2184623761","https://openalex.org/W2189465200","https://openalex.org/W2216541755","https://openalex.org/W2395323716","https://openalex.org/W2411006959","https://openalex.org/W2435648513","https://openalex.org/W2535724050","https://openalex.org/W2547190417","https://openalex.org/W2949813383","https://openalex.org/W2963288913","https://openalex.org/W2998715488","https://openalex.org/W3142730227","https://openalex.org/W4238675359","https://openalex.org/W6614148910","https://openalex.org/W6632489444"],"related_works":["https://openalex.org/W4213239787","https://openalex.org/W4377131110","https://openalex.org/W2114337652","https://openalex.org/W4388857216","https://openalex.org/W2046590706","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W1587991081","https://openalex.org/W2949444602","https://openalex.org/W2989751065"],"abstract_inverted_index":{"Linear":[0],"algebra":[1,70,118,160],"operations":[2,161],"are":[3,93],"at":[4],"the":[5,14,21,50,137,149,198,213],"core":[6],"of":[7,20,41,98,130,151,200,216],"many":[8],"Machine":[9],"Learning":[10],"(ML)":[11],"programs.":[12],"At":[13],"same":[15],"time,":[16],"a":[17,34,124,170],"considerable":[18],"amount":[19],"effort":[22],"for":[23,48,60,73],"solving":[24],"data":[25,31],"analytics":[26],"problems":[27],"is":[28],"spent":[29],"in":[30,140,197,223],"preparation.":[32],"As":[33,123],"result,":[35,125],"end-to-end":[36],"ML":[37],"pipelines":[38,80,92,126,221],"often":[39],"consist":[40],"(":[42,53,66],"i":[43],")":[44,55,68],"relational":[45,110,157],"operators":[46,71,111,119,131],"used":[47,59,72],"joining":[49],"input":[51],"data,":[52],"ii":[54],"user":[56],"defined":[57],"functions":[58],"feature":[61],"extraction":[62],"and":[63,65,76,158,194,212],"vectorization,":[64],"iii":[67],"linear":[69,117,159],"model":[74],"training":[75],"cross-validation.":[77],"Often,":[78],"these":[79,91],"need":[81],"to":[82,85,136,210,219],"scale":[83],"out":[84],"large":[86],"datasets.":[87,114],"In":[88,144],"this":[89,145],"case,":[90],"usually":[94],"implemented":[95,222],"on":[96,112],"top":[97],"dataflow":[99,107,202],"engines":[100,108],"like":[101],"Hadoop,":[102],"Spark,":[103],"or":[104],"Flink.":[105],"These":[106],"implement":[109],"row-partitioned":[113],"However,":[115],"efficient":[116],"use":[120],"block-partitioned":[121,177],"matrices.":[122],"combining":[127],"both":[128],"kinds":[129],"require":[132],"rather":[133],"expensive":[134],"changes":[135],"physical":[138,164],"representation,":[139],"particular":[141],"re-partitioning":[142],"steps.":[143],"paper,":[146],"we":[147],"investigate":[148],"potential":[150],"reducing":[152],"shuffling":[153,181],"costs":[154],"by":[155],"fusing":[156],"into":[162],"specialized":[163],"operators.":[165],"We":[166],"present":[167],"BlockJoin":[168,183,217],",":[169],"distributed":[171],"join":[172],"algorithm":[173],"which":[174],"directly":[175],"produces":[176],"results.":[178],"To":[179],"minimize":[180],"costs,":[182],"applies":[184],"database":[185],"techniques":[186],"known":[187],"from":[188],"columnar":[189],"processing,":[190],"such":[191],"as":[192],"index-joins":[193],"late":[195],"materialization,":[196],"context":[199],"parallel":[201],"engines.":[203],"Our":[204],"experimental":[205],"evaluation":[206],"shows":[207],"speedups":[208],"up":[209],"6\u00d7":[211],"skew":[214],"resistance":[215],"compared":[218],"state-of-the-art":[220],"Spark.":[224]},"counts_by_year":[{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2017-11-10T00:00:00"}