{"id":"https://openalex.org/W3112261684","doi":"https://doi.org/10.1109/bigdata52589.2021.9671575","title":"Building Graphs at a Large Scale: Union Find Shuffle","display_name":"Building Graphs at a Large Scale: Union Find Shuffle","publication_year":2021,"publication_date":"2021-12-15","ids":{"openalex":"https://openalex.org/W3112261684","doi":"https://doi.org/10.1109/bigdata52589.2021.9671575","mag":"3112261684"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata52589.2021.9671575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671575","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2012.05430","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109908998","display_name":"Saigopal Thota","orcid":null},"institutions":[{"id":"https://openalex.org/I1330693074","display_name":"Walmart (United States)","ror":"https://ror.org/04j0gge90","country_code":"US","type":"company","lineage":["https://openalex.org/I1330693074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Saigopal Thota","raw_affiliation_strings":["Walmart Inc"],"affiliations":[{"raw_affiliation_string":"Walmart Inc","institution_ids":["https://openalex.org/I1330693074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038268595","display_name":"Mridul Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I1330693074","display_name":"Walmart (United States)","ror":"https://ror.org/04j0gge90","country_code":"US","type":"company","lineage":["https://openalex.org/I1330693074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mridul Jain","raw_affiliation_strings":["Walmart Inc"],"affiliations":[{"raw_affiliation_string":"Walmart Inc","institution_ids":["https://openalex.org/I1330693074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066349386","display_name":"Nishad Kamat","orcid":null},"institutions":[{"id":"https://openalex.org/I1330693074","display_name":"Walmart (United States)","ror":"https://ror.org/04j0gge90","country_code":"US","type":"company","lineage":["https://openalex.org/I1330693074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nishad Kamat","raw_affiliation_strings":["Walmart Inc"],"affiliations":[{"raw_affiliation_string":"Walmart Inc","institution_ids":["https://openalex.org/I1330693074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091725247","display_name":"Saikiran Malikireddy","orcid":null},"institutions":[{"id":"https://openalex.org/I1330693074","display_name":"Walmart (United States)","ror":"https://ror.org/04j0gge90","country_code":"US","type":"company","lineage":["https://openalex.org/I1330693074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saikiran Malikireddy","raw_affiliation_strings":["Walmart Inc"],"affiliations":[{"raw_affiliation_string":"Walmart Inc","institution_ids":["https://openalex.org/I1330693074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038375179","display_name":"Pruthvi Raj Eranti","orcid":null},"institutions":[{"id":"https://openalex.org/I1330693074","display_name":"Walmart (United States)","ror":"https://ror.org/04j0gge90","country_code":"US","type":"company","lineage":["https://openalex.org/I1330693074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pruthvi Raj Eranti","raw_affiliation_strings":["Walmart Inc"],"affiliations":[{"raw_affiliation_string":"Walmart Inc","institution_ids":["https://openalex.org/I1330693074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072720724","display_name":"Albin Kuruvilla","orcid":null},"institutions":[{"id":"https://openalex.org/I1330693074","display_name":"Walmart (United States)","ror":"https://ror.org/04j0gge90","country_code":"US","type":"company","lineage":["https://openalex.org/I1330693074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Albin Kuruvilla","raw_affiliation_strings":["Walmart Inc","Walmart Labs"],"affiliations":[{"raw_affiliation_string":"Walmart Inc","institution_ids":["https://openalex.org/I1330693074"]},{"raw_affiliation_string":"Walmart Labs","institution_ids":["https://openalex.org/I1330693074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5109908998"],"corresponding_institution_ids":["https://openalex.org/I1330693074"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00214777,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4146","last_page":"4152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987000226974487,"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/T11106","display_name":"Data Management and Algorithms","score":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7805509567260742},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7603440284729004},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5957339406013489},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5750835537910461},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.513442873954773},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.45015376806259155},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.441873162984848},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.428041011095047},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.42271408438682556},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3952561318874359},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.35377174615859985},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.25716233253479004},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2109246850013733},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12529096007347107},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11841842532157898},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.112140953540802}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7805509567260742},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7603440284729004},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5957339406013489},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5750835537910461},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.513442873954773},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.45015376806259155},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.441873162984848},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.428041011095047},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.42271408438682556},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3952561318874359},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.35377174615859985},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.25716233253479004},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2109246850013733},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12529096007347107},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11841842532157898},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.112140953540802},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/bigdata52589.2021.9671575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671575","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2012.05430","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.05430","pdf_url":"https://arxiv.org/pdf/2012.05430","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3112261684","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2012.05430.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2012.05430","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2012.05430","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2012.05430","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.05430","pdf_url":"https://arxiv.org/pdf/2012.05430","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5899999737739563,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3112261684.pdf"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1982003698","https://openalex.org/W1984775058","https://openalex.org/W1993219230","https://openalex.org/W2004350101","https://openalex.org/W2019724001","https://openalex.org/W2053061798","https://openalex.org/W2088011174","https://openalex.org/W2125182537","https://openalex.org/W2166837162","https://openalex.org/W2170616854","https://openalex.org/W2505011268","https://openalex.org/W6651364817","https://openalex.org/W6672570519","https://openalex.org/W6678325626"],"related_works":["https://openalex.org/W3084687783","https://openalex.org/W2011694826","https://openalex.org/W2410199455","https://openalex.org/W94745405","https://openalex.org/W2967927105","https://openalex.org/W2416578472","https://openalex.org/W3161491156","https://openalex.org/W2504760006","https://openalex.org/W2963955033","https://openalex.org/W2585469311","https://openalex.org/W2033548106","https://openalex.org/W2884907962","https://openalex.org/W2027024265","https://openalex.org/W2575707944","https://openalex.org/W1988956076","https://openalex.org/W2207967621","https://openalex.org/W2891155909","https://openalex.org/W3014979397","https://openalex.org/W3103664230","https://openalex.org/W2539215798"],"abstract_inverted_index":{"Large":[0],"scale":[1,41],"graph":[2],"processing":[3],"using":[4],"distributed":[5,26],"computing":[6],"frameworks":[7],"is":[8,59],"becoming":[9],"pervasive":[10],"and":[11,24,42,62,73,111,129],"efficient":[12],"in":[13,132,142],"the":[14,45,51,57,63,66,71,74,97,119,133,143],"industry.":[15],"In":[16],"this":[17],"work,":[18],"we":[19],"present":[20,82],"a":[21,48,102],"highly":[22],"scalable":[23],"configurable":[25],"algorithm":[27,46,98,124],"for":[28],"building":[29],"connected":[30,67,140],"components,":[31],"called":[32],"Union":[33],"Find":[34],"Shuffle":[35],"(UFS)":[36],"with":[37,138],"Path":[38],"Compression.":[39],"The":[40],"complexity":[43,72],"of":[44,50,53,65,85,122,135,145],"are":[47],"function":[49],"number":[52],"partitions":[54],"into":[55],"which":[56,125],"data":[58,137],"initially":[60],"partitioned,":[61],"size":[64,144],"components.":[68],"We":[69,80,117],"discuss":[70],"benchmarks":[75,84],"compared":[76],"to":[77,106],"similar":[78],"approaches.":[79],"also":[81],"current":[83],"our":[86,123],"production":[87],"system,":[88],"running":[89],"on":[90],"commodity":[91],"out-of-the-box":[92],"cloud":[93],"Hadoop":[94],"infrastructure,":[95],"where":[96],"was":[99],"deployed":[100],"over":[101],"year":[103],"ago,":[104],"scaled":[105],"around":[107],"75":[108],"Billion":[109,147],"nodes":[110,148],"60":[112],"Billions":[113],"linkages":[114],"(and":[115],"growing).":[116],"highlight":[118],"key":[120],"aspects":[121],"enable":[126],"seamless":[127],"scaling":[128],"performance":[130],"even":[131],"presence":[134],"skewed":[136],"large":[139],"components":[141],"10":[146],"each.":[149]},"counts_by_year":[],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}