{"id":"https://openalex.org/W4411403220","doi":"https://doi.org/10.1145/3725303","title":"Rule-Based Graph Cleaning with GPUs on a Single Machine","display_name":"Rule-Based Graph Cleaning with GPUs on a Single Machine","publication_year":2025,"publication_date":"2025-06-17","ids":{"openalex":"https://openalex.org/W4411403220","doi":"https://doi.org/10.1145/3725303"},"language":"en","primary_location":{"id":"doi:10.1145/3725303","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3725303","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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 ACM on Management of Data","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/A5118330965","display_name":"Wenchao Bai","orcid":"https://orcid.org/0009-0001-1632-4347"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenchao Bai","raw_affiliation_strings":["Southeast University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0009-0001-1632-4347","affiliations":[{"raw_affiliation_string":"Southeast University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070565287","display_name":"Wenfei Fan","orcid":"https://orcid.org/0000-0001-5149-2656"},"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"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Wenfei Fan","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, Shenzhen, Guangdong, China, University of Edinburgh, Edinburgh, Scotland, United Kingdom, and Beihang University, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5149-2656","affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, Shenzhen, Guangdong, China, University of Edinburgh, Edinburgh, Scotland, United Kingdom, and Beihang University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I82880672","https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100759864","display_name":"Shuhao Liu","orcid":"https://orcid.org/0000-0002-4892-0979"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuhao Liu","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-4892-0979","affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, Shenzhen, Guangdong, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085916746","display_name":"K.K. Pang","orcid":"https://orcid.org/0009-0006-4086-1421"},"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":"Kehan Pang","raw_affiliation_strings":["Beihang University, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-4086-1421","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102784961","display_name":"Xiaoke Zhu","orcid":"https://orcid.org/0000-0001-5701-5279"},"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, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5701-5279","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081458459","display_name":"Jiahui Jin","orcid":"https://orcid.org/0000-0001-9570-1456"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahui Jin","raw_affiliation_strings":["Southeast University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0001-9570-1456","affiliations":[{"raw_affiliation_string":"Southeast University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1067636,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":"3","first_page":"1","last_page":"27"},"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9983000159263611,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9883000254631042,"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":0.8832613229751587},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6183035969734192},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5057411193847656},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4807688891887665},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.47441408038139343},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4695233404636383},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.46391382813453674},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.43376386165618896},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2905566692352295},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.26604562997817993},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10258901119232178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8832613229751587},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6183035969734192},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5057411193847656},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4807688891887665},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.47441408038139343},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4695233404636383},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.46391382813453674},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.43376386165618896},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2905566692352295},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26604562997817993},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10258901119232178},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3725303","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3725303","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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 ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4776362585","display_name":null,"funder_award_id":"62232004","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1181317657","https://openalex.org/W1480292905","https://openalex.org/W1734573275","https://openalex.org/W1862165198","https://openalex.org/W1990391007","https://openalex.org/W2011039300","https://openalex.org/W2034102265","https://openalex.org/W2050171146","https://openalex.org/W2053076698","https://openalex.org/W2074935284","https://openalex.org/W2077518845","https://openalex.org/W2119407198","https://openalex.org/W2151502664","https://openalex.org/W2160983447","https://openalex.org/W2169940602","https://openalex.org/W2170616854","https://openalex.org/W2425348221","https://openalex.org/W2578829886","https://openalex.org/W2586902511","https://openalex.org/W2612636236","https://openalex.org/W2798649495","https://openalex.org/W2942740455","https://openalex.org/W2957204582","https://openalex.org/W2972270478","https://openalex.org/W2981963339","https://openalex.org/W3014705052","https://openalex.org/W3022260960","https://openalex.org/W3030126027","https://openalex.org/W3030639942","https://openalex.org/W3082965822","https://openalex.org/W3093053585","https://openalex.org/W3123375411","https://openalex.org/W3164237119","https://openalex.org/W3169645941","https://openalex.org/W3196829622","https://openalex.org/W3196961327","https://openalex.org/W4205695952","https://openalex.org/W4206031975","https://openalex.org/W4211032081","https://openalex.org/W4246012463","https://openalex.org/W4283329289","https://openalex.org/W4285602153","https://openalex.org/W4288057690","https://openalex.org/W4301377523","https://openalex.org/W4306317602","https://openalex.org/W4372263931","https://openalex.org/W4383749455","https://openalex.org/W4388661866","https://openalex.org/W4392453103","https://openalex.org/W4403963860","https://openalex.org/W4408061176","https://openalex.org/W6912652508"],"related_works":["https://openalex.org/W2291920536","https://openalex.org/W2022397046","https://openalex.org/W2162726111","https://openalex.org/W1603583590","https://openalex.org/W338671845","https://openalex.org/W1587248296","https://openalex.org/W2117755361","https://openalex.org/W2286348849","https://openalex.org/W2063770303","https://openalex.org/W2018511057"],"abstract_inverted_index":{"This":[0],"paper":[1],"studies":[2],"cost-effective":[3],"graph":[4,50],"cleaning":[5,27,98],"with":[6,28,123,168],"a":[7,12,55,59,94,104,109,131],"single":[8,110],"machine.":[9],"We":[10],"adopt":[11],"rule-based":[13],"method":[14],"that":[15,106,154],"may":[16],"embed":[17],"machine":[18,111],"learning":[19],"models":[20],"as":[21,45],"predicates":[22],"in":[23],"the":[24,29,157],"rules.":[25],"Graph":[26],"rules":[30],"involves":[31],"rule":[32],"discovery,":[33],"error":[34],"detection":[35],"and":[36,43,53,116,126,129,138,141,165],"correction.":[37],"These":[38],"tasks":[39,82],"are":[40],"both":[41],"computation-heavy":[42],"I/O-intensive":[44],"they":[46],"repeatedly":[47],"invoke":[48],"costly":[49],"pattern":[51],"matching,":[52],"produce":[54],"large":[56,60,99],"amount":[57],"of":[58,62,70],"volume":[61],"intermediate":[63],"results,":[64],"among":[65],"other":[66],"things.":[67],"In":[68],"light":[69],"these,":[71],"no":[72],"existing":[73],"single-machine":[74,95,159],"system":[75,96],"is":[76],"able":[77],"to":[78,144],"carry":[79],"out":[80],"these":[81],"even":[83,87],"on":[84],"not-too-large":[85],"graphs,":[86,150],"using":[88],"GPUs.":[89],"Thus":[90],"we":[91,151],"develop":[92],"MiniClean,":[93],"for":[97,135],"graphs.":[100],"It":[101],"proposes":[102],"(1)":[103],"workflow":[105],"better":[107],"fits":[108],"by":[112,161,171],"pipelining":[113],"CPU,":[114],"GPU":[115],"I/O":[117],"operations;":[118],"(2)":[119],"memory":[120],"footprint":[121],"reduction":[122],"bundled":[124],"processing":[125],"data":[127],"compression;":[128],"(3)":[130],"multi-mode":[132],"parallel":[133],"model":[134],"SIMD,":[136],"pipelined":[137],"independent":[139],"parallelism,":[140],"their":[142],"scheduling":[143],"maximize":[145],"CPU--GPU":[146],"synergy.":[147],"Using":[148],"real-life":[149],"empirically":[152],"verify":[153],"MiniClean":[155],"outperforms":[156],"SOTA":[158],"systems":[160,167],"at":[162,172],"least":[163,173],"65.34\u00d7":[164],"multi-machine":[166],"32":[169],"nodes":[170],"8.09\u00d7.":[174]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}