{"id":"https://openalex.org/W3124235191","doi":"https://doi.org/10.1145/3428757.3429140","title":"Analysis and Comparison of Block-Splitting-Based Load Balancing Strategies for Parallel Entity Resolution","display_name":"Analysis and Comparison of Block-Splitting-Based Load Balancing Strategies for Parallel Entity Resolution","publication_year":2020,"publication_date":"2020-11-30","ids":{"openalex":"https://openalex.org/W3124235191","doi":"https://doi.org/10.1145/3428757.3429140","mag":"3124235191"},"language":"en","primary_location":{"id":"doi:10.1145/3428757.3429140","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3428757.3429140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Conference on Information Integration and Web-based Applications &amp; Services","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100373759","display_name":"Xiao Chen","orcid":"https://orcid.org/0000-0003-1941-3449"},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke-Universit\u00e4t Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Xiao Chen","raw_affiliation_strings":["Otto-von-Guericke-University of Magdeburg, Magdeburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Otto-von-Guericke-University of Magdeburg, Magdeburg, Germany","institution_ids":["https://openalex.org/I95793202"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006873691","display_name":"Nishanth Entoor Venkatarathnam","orcid":null},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke-Universit\u00e4t Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nishanth Entoor Venkatarathnam","raw_affiliation_strings":["Otto-von-Guericke-University of Magdeburg, Magdeburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Otto-von-Guericke-University of Magdeburg, Magdeburg, Germany","institution_ids":["https://openalex.org/I95793202"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018680395","display_name":"Kirity Rapuru","orcid":null},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke-Universit\u00e4t Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kirity Rapuru","raw_affiliation_strings":["Otto-von-Guericke-University of Magdeburg, Magdeburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Otto-von-Guericke-University of Magdeburg, Magdeburg, Germany","institution_ids":["https://openalex.org/I95793202"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061367729","display_name":"David Broneske","orcid":"https://orcid.org/0000-0002-9580-740X"},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke-Universit\u00e4t Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"David Broneske","raw_affiliation_strings":["Otto-von-Guericke-University of Magdeburg, Magdeburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Otto-von-Guericke-University of Magdeburg, Magdeburg, Germany","institution_ids":["https://openalex.org/I95793202"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059805666","display_name":"Gabriel Campero Durand","orcid":null},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke-Universit\u00e4t Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gabriel Campero Durand","raw_affiliation_strings":["Otto-von-Guericke-University of Magdeburg, Magdeburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Otto-von-Guericke-University of Magdeburg, Magdeburg, Germany","institution_ids":["https://openalex.org/I95793202"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061275415","display_name":"Roman Zoun","orcid":null},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke-Universit\u00e4t Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Roman Zoun","raw_affiliation_strings":["Otto-von-Guericke-University of Magdeburg, Magdeburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Otto-von-Guericke-University of Magdeburg, Magdeburg, Germany","institution_ids":["https://openalex.org/I95793202"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042946019","display_name":"Gunter Saake","orcid":"https://orcid.org/0000-0001-9576-8474"},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke-Universit\u00e4t Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gunter Saake","raw_affiliation_strings":["Otto-von-Guericke-University of Magdeburg, Magdeburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Otto-von-Guericke-University of Magdeburg, Magdeburg, Germany","institution_ids":["https://openalex.org/I95793202"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95793202"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2784371,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"446","last_page":"455"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9921000003814697,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9904000163078308,"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":0.828590989112854},{"id":"https://openalex.org/keywords/reducer","display_name":"Reducer","score":0.7819733619689941},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6685363054275513},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6334569454193115},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.6234910488128662},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6015528440475464},{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.5706701874732971},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5386564135551453},{"id":"https://openalex.org/keywords/block-size","display_name":"Block size","score":0.5098418593406677},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4464426338672638},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4350129961967468},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4172830879688263},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4090290069580078},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3453986942768097},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3397538363933563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.828590989112854},{"id":"https://openalex.org/C2776985865","wikidata":"https://www.wikidata.org/wiki/Q26820931","display_name":"Reducer","level":2,"score":0.7819733619689941},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6685363054275513},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6334569454193115},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.6234910488128662},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6015528440475464},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.5706701874732971},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5386564135551453},{"id":"https://openalex.org/C41431624","wikidata":"https://www.wikidata.org/wiki/Q1053357","display_name":"Block size","level":3,"score":0.5098418593406677},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4464426338672638},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4350129961967468},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4172830879688263},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4090290069580078},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3453986942768097},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3397538363933563},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C147176958","wikidata":"https://www.wikidata.org/wiki/Q77590","display_name":"Civil engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"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:10.1145/3428757.3429140","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3428757.3429140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Conference on Information Integration and Web-based Applications &amp; Services","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W125869453","https://openalex.org/W1597532222","https://openalex.org/W1969186495","https://openalex.org/W1982538504","https://openalex.org/W2003138918","https://openalex.org/W2035880583","https://openalex.org/W2044280769","https://openalex.org/W2061601738","https://openalex.org/W2070162726","https://openalex.org/W2073459573","https://openalex.org/W2076488383","https://openalex.org/W2080131844","https://openalex.org/W2088835546","https://openalex.org/W2120755171","https://openalex.org/W2122370965","https://openalex.org/W2140509629","https://openalex.org/W2165769837","https://openalex.org/W2397525010","https://openalex.org/W2399133307","https://openalex.org/W2403933246","https://openalex.org/W2464834590","https://openalex.org/W2490088997","https://openalex.org/W2515208787","https://openalex.org/W2537849534","https://openalex.org/W2559870814","https://openalex.org/W2596139470","https://openalex.org/W2795559724","https://openalex.org/W2800195291","https://openalex.org/W2886719180","https://openalex.org/W6635650928","https://openalex.org/W6712438735"],"related_works":["https://openalex.org/W2943236215","https://openalex.org/W2394411596","https://openalex.org/W2737431648","https://openalex.org/W2349055795","https://openalex.org/W4226030716","https://openalex.org/W2599888081","https://openalex.org/W2971039361","https://openalex.org/W2725465928","https://openalex.org/W2358616404","https://openalex.org/W1500978221"],"abstract_inverted_index":{"Entity":[0],"resolution":[1],"(ER)":[2],"is":[3,44,83,170,181],"a":[4,174,176],"process":[5],"to":[6,11,35,48,92,120,183,188,201],"identify":[7],"records":[8],"that":[9,147],"refer":[10],"the":[12,20,50,58,64,78,86,100,122,153,157,160,185,202],"same":[13],"real-world":[14,137],"entity.":[15],"In":[16,95],"recent":[17],"years,":[18],"facing":[19],"ever-increasing":[21],"data":[22],"volume,":[23],"both":[24],"blocking":[25],"techniques":[26],"and":[27,40,46,75,102,110,112,118,128,138,194],"parallel":[28,55],"computation":[29],"have":[30,196],"been":[31],"proposed":[32,131],"for":[33,54],"ER":[34],"reduce":[36,184],"its":[37],"running":[38],"time":[39,187],"improve":[41,93,189],"efficiency.":[42,94,190],"It":[43],"popular":[45],"convenient":[47],"apply":[49],"MapReduce":[51],"programming":[52],"model":[53],"computation.":[56],"With":[57],"default":[59],"load":[60,72,155],"balancing":[61],"strategy,":[62],"if":[63],"block":[65,106],"sizes":[66],"are":[67],"skewed,":[68],"an":[69],"imbalanced":[70],"reducer":[71,154],"will":[73],"occur":[74],"significantly":[76],"increase":[77],"runtime.":[79],"One":[80],"possible":[81],"solution":[82],"block-splitting:":[84],"breaking":[85],"overpopulated":[87],"blocks":[88],"into":[89],"smaller":[90],"sub-blocks,":[91],"this":[96],"paper":[97],"we":[98,113],"analyze":[99],"advantages":[101],"disadvantages":[103],"of":[104,149,159,167,179,204],"state-of-the-art":[105],"splitting":[107],"methods":[108],"(BlockSplit":[109],"BlockSlicer),":[111],"propose":[114],"two":[115],"approaches:":[116],"TLS":[117,193],"BOS":[119,195],"overcome":[121],"identified":[123],"drawbacks.":[124],"We":[125],"comprehensively":[126],"evaluate":[127],"compare":[129],"our":[130,192],"solutions,":[132],"with":[133,141,156],"Spark":[134],"implementations,":[135],"using":[136],"synthetic":[139],"datasets":[140],"different":[142],"properties.":[143],"The":[144],"results":[145],"show":[146],"all":[148],"them":[150],"can":[151],"balance":[152],"help":[158],"greedy":[161],"partition":[162],"assignment":[163],"strategy.":[164],"When":[165],"memory":[166],"used":[168],"cluster":[169],"not":[171],"abundant":[172],"given":[173],"dataset,":[175],"high":[177],"number":[178],"reducers":[180],"required":[182],"GC":[186],"Partitcularly,":[191],"overwelmingly":[197],"lower":[198],"overhead":[199],"due":[200],"ability":[203],"block-wise":[205],"composite":[206],"key":[207],"assignment.":[208]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
