{"id":"https://openalex.org/W4408061176","doi":"https://doi.org/10.14778/3705829.3705847","title":"HyperBlocker: Accelerating Rule-Based Blocking in Entity Resolution Using GPUs","display_name":"HyperBlocker: Accelerating Rule-Based Blocking in Entity Resolution Using GPUs","publication_year":2024,"publication_date":"2024-10-01","ids":{"openalex":"https://openalex.org/W4408061176","doi":"https://doi.org/10.14778/3705829.3705847"},"language":"en","primary_location":{"id":"doi:10.14778/3705829.3705847","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3705829.3705847","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/A5012689262","display_name":"Xiaoke Zhu","orcid":"https://orcid.org/0000-0002-0664-1832"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoke Zhu","raw_affiliation_strings":["Beihang University, China and Shenzhen Institute of Computing Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, China and Shenzhen Institute of Computing Sciences, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083685156","display_name":"Min Xie","orcid":"https://orcid.org/0000-0002-2967-3490"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Xie","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100682726","display_name":"Ting Deng","orcid":"https://orcid.org/0000-0001-5477-7972"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Deng","raw_affiliation_strings":["Beihang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111464423","display_name":"Qi Zhang","orcid":"https://orcid.org/0000-0002-2685-7681"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qi Zhang","raw_affiliation_strings":["Meta Platforms, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Platforms, USA","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1926,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.8247232,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"18","issue":"2","first_page":"308","last_page":"321"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9896000027656555,"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"}},{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9872999787330627,"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/blocking","display_name":"Blocking (statistics)","score":0.7525714635848999},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6538481712341309},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.512113094329834},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.4498275816440582},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20772922039031982}],"concepts":[{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.7525714635848999},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6538481712341309},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.512113094329834},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.4498275816440582},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20772922039031982},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3705829.3705847","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3705829.3705847","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2002430341","https://openalex.org/W2009036829","https://openalex.org/W2036971997","https://openalex.org/W2068418796","https://openalex.org/W2070162726","https://openalex.org/W2080638865","https://openalex.org/W2098416578","https://openalex.org/W2100986433","https://openalex.org/W2128793454","https://openalex.org/W2153160273","https://openalex.org/W2169940602","https://openalex.org/W2216499221","https://openalex.org/W2489451554","https://openalex.org/W2492590231","https://openalex.org/W2533003199","https://openalex.org/W2535168187","https://openalex.org/W2546672044","https://openalex.org/W2615445186","https://openalex.org/W2617941540","https://openalex.org/W2798649495","https://openalex.org/W2798832443","https://openalex.org/W2907714110","https://openalex.org/W2926767350","https://openalex.org/W2957204582","https://openalex.org/W2998702515","https://openalex.org/W3014295153","https://openalex.org/W3014705052","https://openalex.org/W3045854241","https://openalex.org/W3117273852","https://openalex.org/W3123375411","https://openalex.org/W3164439293","https://openalex.org/W3175890395","https://openalex.org/W3197468999","https://openalex.org/W4206031975","https://openalex.org/W4214588406","https://openalex.org/W4232946860","https://openalex.org/W4246012463","https://openalex.org/W4281879035","https://openalex.org/W4289533994","https://openalex.org/W4386768666","https://openalex.org/W6646982788"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2392835431","https://openalex.org/W2126932387","https://openalex.org/W1965371215","https://openalex.org/W2353762239","https://openalex.org/W66314852","https://openalex.org/W2185938410","https://openalex.org/W2484966135"],"abstract_inverted_index":{"This":[0],"paper":[1],"studies":[2],"rule-based":[3],"blocking":[4,16,23,27],"in":[5,17],"Entity":[6],"Resolution":[7],"(ER).":[8],"We":[9],"propose":[10],"HyperBlocker,":[11],"a":[12,31,43,59],"GPU-accelerated":[13],"system":[14],"for":[15,51],"ER.":[18],"As":[19],"opposed":[20],"to":[21,34,64],"previous":[22],"algorithms":[24],"and":[25,38,45,57,81,89],"parallel":[26],"solvers,":[28,92],"HyperBlocker":[29,76,98],"employs":[30],"pipelined":[32],"architecture":[33],"overlap":[35],"data":[36],"transfer":[37],"GPU":[39],"operations.":[40],"It":[41],"generates":[42],"data-aware":[44],"rule-aware":[46],"execution":[47],"plan":[48],"on":[49,68],"CPUs,":[50],"specifying":[52],"how":[53],"rules":[54],"are":[55],"evaluated,":[56],"develops":[58],"number":[60],"of":[61],"hardware-aware":[62],"optimizations":[63],"achieve":[65],"massive":[66],"parallelism":[67],"GPUs.":[69],"Using":[70],"real-life":[71],"datasets,":[72],"we":[73,104],"show":[74],"that":[75],"is":[77],"at":[78,113],"least":[79,114],"6.8\u00d7":[80],"9.1\u00d7":[82],"faster":[83],"than":[84],"prior":[85],"CPU-powered":[86],"distributed":[87],"systems":[88],"GPU-based":[90],"ER":[91,102,110],"respectively.":[93],"Better":[94],"still,":[95],"by":[96,112],"combining":[97],"with":[99,116],"the":[100,108],"state-of-the-art":[101],"matcher,":[103],"can":[105],"speed":[106],"up":[107],"overall":[109],"process":[111],"30%":[115],"comparable":[117],"accuracy.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}