{"id":"https://openalex.org/W7138929240","doi":"https://doi.org/10.1145/3802127","title":"Workload-Aware Incremental Reclustering in Cloud Data Warehouses","display_name":"Workload-Aware Incremental Reclustering in Cloud Data Warehouses","publication_year":2026,"publication_date":"2026-05-18","ids":{"openalex":"https://openalex.org/W7138929240","doi":"https://doi.org/10.1145/3802127"},"language":"en","primary_location":{"id":"doi:10.1145/3802127","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3802127","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3802127","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100610065","display_name":"Yipeng Liu","orcid":"https://orcid.org/0000-0003-2084-8781"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yipeng Liu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-0429-3011","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088368179","display_name":"Renfei Zhou","orcid":"https://orcid.org/0000-0002-0095-0626"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Renfei Zhou","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0002-0095-0626","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136380625","display_name":"Jiaqi Yan","orcid":"https://orcid.org/0009-0008-5297-7557"},"institutions":[{"id":"https://openalex.org/I4210151393","display_name":"Universidad San Carlos","ror":"https://ror.org/05b1ymr19","country_code":"PY","type":"education","lineage":["https://openalex.org/I4210151393"]}],"countries":["PY"],"is_corresponding":false,"raw_author_name":"Jiaqi Yan","raw_affiliation_strings":["Snowflake Inc., San Carlos, USA"],"raw_orcid":"https://orcid.org/0009-0008-5297-7557","affiliations":[{"raw_affiliation_string":"Snowflake Inc., San Carlos, USA","institution_ids":["https://openalex.org/I4210151393"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136434322","display_name":"Huanchen Zhang","orcid":"https://orcid.org/0009-0001-4821-1558"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huanchen Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-4821-1558","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":19.1314,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.98305877,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"4","issue":"3","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.3587999939918518,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.3587999939918518,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.2565000057220459,"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/T11719","display_name":"Data Quality and Management","score":0.12919999659061432,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6942999958992004},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6295999884605408},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6226000189781189},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.6104000210762024},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5873000025749207},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.553600013256073},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5418000221252441},{"id":"https://openalex.org/keywords/materialized-view","display_name":"Materialized view","score":0.5052000284194946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8345999717712402},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6942999958992004},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6295999884605408},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6226000189781189},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.6104000210762024},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6031000018119812},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5873000025749207},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.553600013256073},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5418000221252441},{"id":"https://openalex.org/C98199447","wikidata":"https://www.wikidata.org/wiki/Q2445044","display_name":"Materialized view","level":4,"score":0.5052000284194946},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4837999939918518},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.39629998803138733},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.35190001130104065},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33799999952316284},{"id":"https://openalex.org/C54239708","wikidata":"https://www.wikidata.org/wiki/Q1329910","display_name":"View","level":3,"score":0.3375000059604645},{"id":"https://openalex.org/C2779599972","wikidata":"https://www.wikidata.org/wiki/Q82231","display_name":"NoSQL","level":3,"score":0.33730000257492065},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C19012869","wikidata":"https://www.wikidata.org/wiki/Q578372","display_name":"Response time","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.27140000462532043},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3802127","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3802127","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2602.23289","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.23289","pdf_url":"https://arxiv.org/pdf/2602.23289","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3802127","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3802127","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5504056811332703,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G4417073627","display_name":null,"funder_award_id":"62532001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modern":[0],"cloud":[1,44],"data":[2,5,16,22,32,48],"warehouses":[3],"store":[4],"in":[6,24,42],"micro-partitions":[7,71,93],"and":[8,50,62,89,132,139,150],"rely":[9],"on":[10,74,134],"metadata":[11],"(e.g.,":[12],"zonemaps)":[13],"for":[14,30,96],"efficient":[15],"pruning":[17,97],"during":[18],"query":[19,78,109,148],"processing.":[20],"Maintaining":[21],"clustering":[23,36],"a":[25,56,84,118,128,140],"large-scale":[26],"table":[27,107],"is":[28],"crucial":[29],"effective":[31],"pruning.":[33],"Existing":[34],"automatic":[35],"approaches":[37],"lack":[38],"the":[39,67,75,125,152],"flexibility":[40],"required":[41],"dynamic":[43],"environments":[45],"with":[46,117],"continuous":[47],"ingestion":[49],"evolving":[51],"workloads.":[52],"This":[53],"paper":[54],"advocates":[55],"clean":[57],"separation":[58],"between":[59],"reclustering":[60,115,130],"policy":[61],"clustering-key":[63],"selection.":[64],"We":[65,80,122],"introduce":[66],"concept":[68],"of":[69,77],"boundary":[70,76,92],"that":[72,145],"sit":[73],"ranges.":[79],"then":[81],"present":[82],"WAIR,":[83],"workload-aware":[85],"algorithm":[86,126],"to":[87,104,156],"identify":[88],"recluster":[90],"only":[91],"most":[94],"critical":[95],"efficiency.":[98],"WAIR":[99,146],"achieves":[100],"near-optimal":[101],"(with":[102],"respect":[103],"fully":[105],"sorted":[106],"layouts)":[108],"performance":[110,149],"but":[111],"incurs":[112],"significantly":[113],"lower":[114],"cost":[116,154],"theoretical":[119],"upper":[120],"bound.":[121],"further":[123],"implement":[124],"into":[127],"prototype":[129],"service":[131],"evaluate":[133],"standard":[135],"benchmarks":[136],"(TPC-H,":[137],"DSB)":[138],"real-world":[141],"workload.":[142],"Results":[143],"show":[144],"improves":[147],"reduces":[151],"overall":[153],"compared":[155],"existing":[157],"solutions.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2026-03-02T00:00:00"}