{"id":"https://openalex.org/W4390647563","doi":"https://doi.org/10.1145/3639269","title":"Starling: An I/O-Efficient Disk-Resident Graph Index Framework for High-Dimensional Vector Similarity Search on Data Segment","display_name":"Starling: An I/O-Efficient Disk-Resident Graph Index Framework for High-Dimensional Vector Similarity Search on Data Segment","publication_year":2024,"publication_date":"2024-03-12","ids":{"openalex":"https://openalex.org/W4390647563","doi":"https://doi.org/10.1145/3639269"},"language":"en","primary_location":{"id":"doi:10.1145/3639269","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3639269","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2401.02116","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043365458","display_name":"Mengzhao Wang","orcid":"https://orcid.org/0000-0003-3806-1012"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengzhao Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3806-1012","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101811312","display_name":"Weizhi Xu","orcid":"https://orcid.org/0009-0006-7384-7212"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weizhi Xu","raw_affiliation_strings":["Zilliz, Redwood City, USA"],"raw_orcid":"https://orcid.org/0009-0006-7384-7212","affiliations":[{"raw_affiliation_string":"Zilliz, Redwood City, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030490314","display_name":"Xiaomeng Yi","orcid":"https://orcid.org/0000-0001-5792-9994"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaomeng Yi","raw_affiliation_strings":["Zhejiang Lab, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5792-9994","affiliations":[{"raw_affiliation_string":"Zhejiang Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101739083","display_name":"Songlin Wu","orcid":"https://orcid.org/0009-0005-3560-436X"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songlin Wu","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-3560-436X","affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063263224","display_name":"Zhangyang Peng","orcid":"https://orcid.org/0009-0002-5383-9750"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhangyang Peng","raw_affiliation_strings":["Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-5383-9750","affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071521429","display_name":"Xiangyu Ke","orcid":"https://orcid.org/0000-0001-8082-7398"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Ke","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8082-7398","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006238145","display_name":"Yunjun Gao","orcid":"https://orcid.org/0000-0003-3816-8450"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunjun Gao","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3816-8450","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063412515","display_name":"Xiaoliang Xu","orcid":"https://orcid.org/0000-0001-8040-6809"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoliang Xu","raw_affiliation_strings":["Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8040-6809","affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039473179","display_name":"Rentong Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rentong Guo","raw_affiliation_strings":["Zilliz, Redwood City, USA"],"raw_orcid":"https://orcid.org/0009-0007-6895-8185","affiliations":[{"raw_affiliation_string":"Zilliz, Redwood City, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102908205","display_name":"Charles Xie","orcid":"https://orcid.org/0009-0000-1713-8696"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Charles Xie","raw_affiliation_strings":["Zilliz, Redwood City, USA"],"raw_orcid":"https://orcid.org/0009-0000-1713-8696","affiliations":[{"raw_affiliation_string":"Zilliz, Redwood City, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.3739,"has_fulltext":true,"cited_by_count":52,"citation_normalized_percentile":{"value":0.99086524,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"2","issue":"1","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994999766349792,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994999766349792,"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/T11106","display_name":"Data Management and Algorithms","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6871053576469421},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5579111576080322},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.47622591257095337},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39612704515457153},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3769283592700958},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3121287524700165},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2845352292060852}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6871053576469421},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5579111576080322},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47622591257095337},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39612704515457153},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3769283592700958},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3121287524700165},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2845352292060852}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3639269","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3639269","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"},{"id":"pmh:oai:arXiv.org:2401.02116","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.02116","pdf_url":"https://arxiv.org/pdf/2401.02116","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"pmh:oai:arXiv.org:2401.02116","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.02116","pdf_url":"https://arxiv.org/pdf/2401.02116","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1701250793","display_name":null,"funder_award_id":"2023C03198,2021C03156","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G3188578225","display_name":null,"funder_award_id":"U23A20296","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3954808999","display_name":null,"funder_award_id":"62025206,U23A20296","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G5410940137","display_name":null,"funder_award_id":"62025206","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"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390647563.pdf","grobid_xml":"https://content.openalex.org/works/W4390647563.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1986693891","https://openalex.org/W2006759076","https://openalex.org/W2034102265","https://openalex.org/W2086504823","https://openalex.org/W2110026675","https://openalex.org/W2113513143","https://openalex.org/W2118123209","https://openalex.org/W2123838366","https://openalex.org/W2124509324","https://openalex.org/W2170616854","https://openalex.org/W2204555070","https://openalex.org/W2294518132","https://openalex.org/W2309560168","https://openalex.org/W2512971201","https://openalex.org/W2737041163","https://openalex.org/W2742272831","https://openalex.org/W2808787330","https://openalex.org/W2889350994","https://openalex.org/W2901613577","https://openalex.org/W2948637333","https://openalex.org/W2963265099","https://openalex.org/W2963284996","https://openalex.org/W2963469388","https://openalex.org/W2981645762","https://openalex.org/W2984806015","https://openalex.org/W2999480577","https://openalex.org/W3006878628","https://openalex.org/W3029079605","https://openalex.org/W3036320503","https://openalex.org/W3037277842","https://openalex.org/W3037818944","https://openalex.org/W3085011441","https://openalex.org/W3093834826","https://openalex.org/W3098468692","https://openalex.org/W3174354514","https://openalex.org/W3174809957","https://openalex.org/W3196481040","https://openalex.org/W4224330113","https://openalex.org/W4280585778","https://openalex.org/W4285355789","https://openalex.org/W4306317682","https://openalex.org/W4312285477","https://openalex.org/W4312335633","https://openalex.org/W4313050727"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W4235240664","https://openalex.org/W2965083567","https://openalex.org/W1838576100","https://openalex.org/W2095886385","https://openalex.org/W2889616422","https://openalex.org/W2089704382","https://openalex.org/W1983399550","https://openalex.org/W97075385","https://openalex.org/W3151146928"],"abstract_inverted_index":{"High-dimensional":[0],"vector":[1,20,50,69,186],"similarity":[2],"search":[3,135,164,176],"(HVSS)":[4],"is":[5],"gaining":[6],"prominence":[7],"as":[8,108],"a":[9,27,72,94,146,155,174,202],"powerful":[10],"tool":[11],"for":[12,61,78],"various":[13],"data":[14,21,51,62,132,147,203],"science":[15],"and":[16,48,90,100,134,154,167,172,197,208,230,234],"AI":[17],"applications.":[18],"As":[19],"scales":[22],"up,":[23],"in-memory":[24,151],"indexes":[25],"pose":[26],"significant":[28],"challenge":[29],"due":[30],"to":[31,65,179,216,255],"the":[32,138,163,194,260],"substantial":[33],"increase":[34],"in":[35,68,220],"main":[36],"memory":[37,89,207],"requirements.":[38],"A":[39],"potential":[40],"solution":[41],"involves":[42],"leveraging":[43],"disk-based":[44,104,157],"implementation,":[45],"which":[46],"stores":[47],"searches":[49],"on":[52],"high-performance":[53],"devices":[54],"like":[55],"NVMe":[56],"SSDs.":[57],"However,":[58],"implementing":[59],"HVSS":[60,224],"segments":[63,77],"proves":[64],"be":[66],"intricate":[67],"databases":[70],"where":[71],"single":[73],"machine":[74],"comprises":[75],"multiple":[76],"system":[79],"scalability.":[80],"In":[81,118],"this":[82,119],"context,":[83],"each":[84],"segment":[85,204],"operates":[86],"with":[87,159,205,225,249],"limited":[88],"disk":[91,169,182,210],"space,":[92],"necessitating":[93],"delicate":[95],"balance":[96],"between":[97],"accuracy,":[98],"efficiency,":[99,196],"space":[101],"cost.":[102],"Existing":[103],"methods":[105,257],"fall":[106],"short":[107],"they":[109],"do":[110],"not":[111],"holistically":[112],"address":[113],"all":[114],"these":[115],"requirements":[116],"simultaneously.":[117],"paper,":[120],"we":[121,192],"present":[122],"Starling,":[123],"an":[124,150],"I/O-efficient":[125],"disk-resident":[126],"graph":[127,153,158],"index":[128],"framework":[129],"that":[130],"optimizes":[131],"layout":[133,148],"strategy":[136,177],"within":[137],"segment.":[139],"It":[140],"has":[141],"two":[142],"primary":[143],"components:":[144],"(1)":[145],"incorporating":[149],"navigation":[152],"reordered":[156],"enhanced":[160],"locality,":[161],"reducing":[162],"path":[165],"length":[166],"minimizing":[168],"bandwidth":[170],"wastage;":[171],"(2)":[173],"block":[175],"designed":[178],"minimize":[180],"costly":[181],"I/O":[183],"operations":[184],"during":[185],"query":[187,252],"execution.":[188],"Through":[189],"extensive":[190],"experiments,":[191],"validate":[193],"effectiveness,":[195],"scalability":[198],"of":[199,263],"Starling.":[200],"On":[201],"2GB":[206],"10GB":[209],"capacity,":[211],"Starling":[212],"can":[213],"accommodate":[214],"up":[215],"33":[217],"million":[218],"vectors":[219],"128":[221],"dimensions,":[222],"offering":[223],"over":[226],"0.9":[227],"average":[228],"precision":[229],"top-10":[231],"recall":[232],"rate,":[233],"latency":[235,253],"under":[236],"1":[237],"millisecond.":[238],"The":[239],"results":[240],"showcase":[241],"Starling's":[242],"superior":[243],"performance,":[244],"exhibiting":[245],"43.9x":[246],"higher":[247],"throughput":[248],"98%":[250],"lower":[251],"compared":[254],"state-of-the-art":[256],"while":[258],"maintaining":[259],"same":[261],"level":[262],"accuracy.":[264]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":35},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2024-01-10T00:00:00"}