{"id":"https://openalex.org/W4380433180","doi":"https://doi.org/10.1145/3588948","title":"Grep: A Graph Learning Based Database Partitioning System","display_name":"Grep: A Graph Learning Based Database Partitioning System","publication_year":2023,"publication_date":"2023-05-26","ids":{"openalex":"https://openalex.org/W4380433180","doi":"https://doi.org/10.1145/3588948"},"language":"en","primary_location":{"id":"doi:10.1145/3588948","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3588948","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":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3588948","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056912386","display_name":"Xuanhe Zhou","orcid":"https://orcid.org/0000-0002-2285-7836"},"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":true,"raw_author_name":"Xuanhe Zhou","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451576","display_name":"Guoliang Li","orcid":"https://orcid.org/0000-0002-1398-0621"},"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":"Guoliang Li","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114832221","display_name":"Jianhua Feng","orcid":"https://orcid.org/0009-0000-0537-7083"},"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":"Jianhua Feng","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003339985","display_name":"Luyang Liu","orcid":"https://orcid.org/0009-0003-1198-9985"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luyang Liu","raw_affiliation_strings":["Huawei, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067127285","display_name":"Wei Guo","orcid":"https://orcid.org/0009-0008-5952-3515"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Guo","raw_affiliation_strings":["Huawei, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5056912386"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.7604,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.87508542,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"1","issue":"1","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9993000030517578,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9970999956130981,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9932000041007996,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8239499926567078},{"id":"https://openalex.org/keywords/graph-partition","display_name":"Graph partition","score":0.5779539346694946},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5143769383430481},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4307311773300171},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.43048447370529175},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4138437807559967},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41018766164779663},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3542236089706421}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8239499926567078},{"id":"https://openalex.org/C48903430","wikidata":"https://www.wikidata.org/wiki/Q491370","display_name":"Graph partition","level":3,"score":0.5779539346694946},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5143769383430481},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4307311773300171},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.43048447370529175},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4138437807559967},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41018766164779663},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3542236089706421},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3588948","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3588948","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"}],"best_oa_location":{"id":"doi:10.1145/3588948","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3588948","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":[],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4363317473","display_name":null,"funder_award_id":"61925205,62232009,62102215","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5725260554","display_name":null,"funder_award_id":"62232009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7169141996","display_name":null,"funder_award_id":"62102215","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G831406350","display_name":null,"funder_award_id":"61925205","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G962252204","display_name":null,"funder_award_id":"61925205, 62232009, 62102215","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322183","display_name":"Huawei Technologies","ror":"https://ror.org/00cmhce21"},{"id":"https://openalex.org/F4320329777","display_name":"Beijing National Research Center For Information Science And Technology","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1964144121","https://openalex.org/W1971885140","https://openalex.org/W1981988185","https://openalex.org/W2040428289","https://openalex.org/W2075712468","https://openalex.org/W2094140553","https://openalex.org/W2105252819","https://openalex.org/W2133741724","https://openalex.org/W2195388612","https://openalex.org/W2396309311","https://openalex.org/W2426624872","https://openalex.org/W2558460151","https://openalex.org/W2579029018","https://openalex.org/W2583754181","https://openalex.org/W2613136061","https://openalex.org/W2788919350","https://openalex.org/W2848245559","https://openalex.org/W2941003455","https://openalex.org/W2945539433","https://openalex.org/W2949044932","https://openalex.org/W2964218959","https://openalex.org/W2970851599","https://openalex.org/W2983968971","https://openalex.org/W2987119394","https://openalex.org/W2998249308","https://openalex.org/W3007086929","https://openalex.org/W3025775630","https://openalex.org/W3029327553","https://openalex.org/W3029535034","https://openalex.org/W3104631761","https://openalex.org/W3173850788","https://openalex.org/W3176419577","https://openalex.org/W3196849431","https://openalex.org/W3198839277","https://openalex.org/W4205381461","https://openalex.org/W4206064074","https://openalex.org/W4206830372","https://openalex.org/W4210500228","https://openalex.org/W4242142158","https://openalex.org/W4281753793","https://openalex.org/W4282556381","https://openalex.org/W4289533888","https://openalex.org/W4317639412","https://openalex.org/W4317641620","https://openalex.org/W4366504025"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W1974414866","https://openalex.org/W3139829055","https://openalex.org/W2583811263","https://openalex.org/W3211941742","https://openalex.org/W2035944803"],"abstract_inverted_index":{"Database":[0],"partitioning":[1,17,25,57,145,195,218,234,238],"is":[2,45,128],"a":[3,16,102,123,129,141,151,212,246,266],"fundamental":[4],"but":[5],"challenging":[6],"task":[7],"in":[8,36,119,200,245,265],"distributed":[9,49,248],"databases,":[10],"which":[11,59,127],"selects":[12],"specific":[13],"columns":[14,172],"as":[15],"key":[18,26],"for":[19,262],"each":[20],"table":[21,30],"and":[22,47,86,90,133,157,168,206,250],"uses":[23],"the":[24,29,40,56,82,113,169,177,194,204,222,233,239,253],"to":[27,38,53,100,110,121,154,192,202,215,231],"allocate":[28],"data":[31,84,114,156,182,205],"into":[32,115,197],"different":[33,97,116],"compute":[34,98,117],"nodes":[35,99,118],"order":[37,120,201],"maximize":[39],"performance.":[41],"However,":[42],"this":[43],"problem":[44],"NP-hard":[46],"existing":[48],"databases":[50],"require":[51],"users":[52],"manually":[54],"specify":[55],"keys,":[58],"may":[60],"cause":[61],"potential":[62],"performance":[63,235],"degradation.":[64],"Although":[65],"reinforcement":[66],"learning":[67],"based":[68,175,220],"methods":[69],"have":[70,74,242],"been":[71],"proposed,":[72],"they":[73,78,105],"several":[75],"limitations.":[76],"First,":[77],"do":[79],"not":[80],"capture":[81,203],"complex":[83],"distributions":[85],"query":[87,158,166,207],"access":[88],"patterns,":[89],"thus":[91],"involve":[92,106],"high":[93],"computation":[94],"cost":[95],"across":[96],"answer":[101],"query.":[103],"Second,":[104],"an":[107,228],"expensive":[108],"step":[109],"repetitively":[111],"partition":[112],"train":[122],"learned":[124,143],"key-selection":[125,213],"model,":[126],"waste":[130],"of":[131,171,255],"time":[132],"resources.":[134],"To":[135],"address":[136],"these":[137],"limitations,":[138],"we":[139,210,226],"propose":[140,211,227],"practical":[142],"database":[144],"system":[146,257],"Grep.":[147],"We":[148,186,241],"first":[149],"adopt":[150],"graph":[152,179,189,223],"model":[153,214,230],"encode":[155],"features,":[159],"where":[160],"vertices":[161],"are":[162,165,173],"columns,":[163],"edges":[164],"relations,":[167],"weights":[170],"computed":[174],"on":[176,221],"localized":[178],"structures":[180],"(e.g.,":[181,258],"diversity,":[183],"joined":[184],"columns).":[185],"then":[187],"utilize":[188],"neural":[190],"networks":[191],"embed":[193],"factors":[196],"embedding":[198],"vectors":[199],"correlations.":[208],"Next":[209],"select":[216],"appropriate":[217],"keys":[219],"model.":[224],"Finally,":[225],"evaluation":[229],"estimate":[232],"without":[236],"actually":[237],"database.":[240],"implemented":[243],"Grep":[244],"commercial":[247],"database,":[249],"experiments":[251],"show":[252],"effectiveness":[254],"our":[256],"68%":[259],"higher":[260],"throughput":[261],"30K":[263],"queries":[264],"real":[267],"banking":[268],"scenario).":[269]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}