{"id":"https://openalex.org/W4413968235","doi":"https://doi.org/10.14778/3746405.3746427","title":"<i>HAKES</i> : Scalable Vector Database for Embedding Search Service","display_name":"<i>HAKES</i> : Scalable Vector Database for Embedding Search Service","publication_year":2025,"publication_date":"2025-05-01","ids":{"openalex":"https://openalex.org/W4413968235","doi":"https://doi.org/10.14778/3746405.3746427"},"language":"en","primary_location":{"id":"doi:10.14778/3746405.3746427","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3746405.3746427","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.12524","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069564014","display_name":"Guoyu Hu","orcid":"https://orcid.org/0009-0005-9463-2045"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Guoyu Hu","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001683040","display_name":"Shaofeng Cai","orcid":"https://orcid.org/0000-0001-8605-076X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shaofeng Cai","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033418193","display_name":"Tien Tuan Anh Dinh","orcid":"https://orcid.org/0000-0002-8158-3636"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tien Tuan Anh Dinh","raw_affiliation_strings":["Deakin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deakin University","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081384517","display_name":"Zhongle Xie","orcid":"https://orcid.org/0000-0002-2924-6974"},"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":"Zhongle Xie","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047917239","display_name":"Cong Yue","orcid":"https://orcid.org/0000-0003-0263-8879"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Cong Yue","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389298","display_name":"Gang Chen","orcid":"https://orcid.org/0000-0002-9597-497X"},"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":"Gang Chen","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024892041","display_name":"Beng Chin Ooi","orcid":"https://orcid.org/0000-0003-4446-1100"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Beng Chin Ooi","raw_affiliation_strings":["Zhejiang University and National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University and National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5069564014"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":3.0131,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.92231269,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"18","issue":"9","first_page":"3049","last_page":"3062"},"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":0.9995999932289124,"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":0.9995999932289124,"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/T11478","display_name":"Caching and Content Delivery","score":0.9977999925613403,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.95169997215271,"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/scalability","display_name":"Scalability","score":0.7106537818908691},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5948827266693115},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5880935192108154},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5830702781677246},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42119815945625305},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20649778842926025}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7106537818908691},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5948827266693115},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5880935192108154},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5830702781677246},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42119815945625305},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20649778842926025}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/3746405.3746427","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3746405.3746427","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"},{"id":"pmh:oai:arXiv.org:2505.12524","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.12524","pdf_url":"https://arxiv.org/pdf/2505.12524","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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:2505.12524","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.12524","pdf_url":"https://arxiv.org/pdf/2505.12524","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1516019649","https://openalex.org/W1583837637","https://openalex.org/W1975410281","https://openalex.org/W1994655805","https://openalex.org/W2077815765","https://openalex.org/W2087946700","https://openalex.org/W2117539524","https://openalex.org/W2124509324","https://openalex.org/W2147717514","https://openalex.org/W2204555070","https://openalex.org/W2604738573","https://openalex.org/W2607662938","https://openalex.org/W2949985202","https://openalex.org/W2963265099","https://openalex.org/W2963284996","https://openalex.org/W2963469388","https://openalex.org/W2964369530","https://openalex.org/W3029693508","https://openalex.org/W3085011441","https://openalex.org/W3099700870","https://openalex.org/W3136183693","https://openalex.org/W3174809957","https://openalex.org/W3201053014","https://openalex.org/W3205509771","https://openalex.org/W4226000737","https://openalex.org/W4284685333","https://openalex.org/W4295885110","https://openalex.org/W4312285477","https://openalex.org/W4366492471","https://openalex.org/W4367046872","https://openalex.org/W4381329139","https://openalex.org/W4381610063","https://openalex.org/W4385568335","https://openalex.org/W4386123432","https://openalex.org/W4387321071","https://openalex.org/W4390647563","https://openalex.org/W4399175194","https://openalex.org/W4401856724"],"related_works":["https://openalex.org/W3024364549","https://openalex.org/W4206019083","https://openalex.org/W2048865712","https://openalex.org/W1976265003","https://openalex.org/W2370378377","https://openalex.org/W2081900870","https://openalex.org/W2130160813","https://openalex.org/W2054476758","https://openalex.org/W2350613701","https://openalex.org/W2000569830"],"abstract_inverted_index":{"Modern":[0],"deep":[1,221],"learning":[2,143,222],"models":[3],"capture":[4],"the":[5,30,51,147,159,177,180,193,235,256],"semantics":[6],"of":[7,179],"complex":[8],"data":[9],"by":[10,175,220],"transforming":[11],"them":[12],"into":[13],"high-dimensional":[14,64,216],"embedding":[15,31,217],"vectors.":[16],"Emerging":[17],"applications,":[18],"such":[19],"as":[20],"retrieval-augmented":[21],"generation,":[22],"use":[23],"approximate":[24],"nearest":[25],"neighbor":[26],"(ANN)":[27],"search":[28,160,173],"in":[29,62,196,234],"vector":[32,39,93,189,213],"space":[33],"to":[34,55,71,84,90,133,145,156,251],"find":[35],"similar":[36],"data.":[37],"Existing":[38],"databases":[40],"provide":[41],"indexes":[42,49,68,209],"for":[43,162,169],"efficient":[44],"ANN":[45,113],"searches,":[46],"with":[47,115,125],"graph-based":[48],"being":[50],"most":[52],"popular":[53],"due":[54],"their":[56],"low":[57],"latency":[58],"and":[59,81,99,129,136,204,210,239,248],"high":[60,97,100,236],"recall":[61,101,237],"real-world":[63],"datasets.":[65],"However,":[66],"these":[67],"are":[69],"costly":[70],"build,":[72],"suffer":[73],"from":[74],"significant":[75],"contention":[76],"under":[77,102,240],"concurrent":[78,103,241],"read-write":[79,104,242],"workloads,":[80],"scale":[82],"poorly":[83],"multiple":[85],"servers.":[86],"Our":[87],"goal":[88],"is":[89,246],"build":[91],"a":[92,121,130,139,187,197],"database":[94,190],"that":[95,191,228],"achieves":[96,249],"throughput":[98],"workloads.":[105,243],"To":[106],"this":[107],"end,":[108],"we":[109,137,166,184],"first":[110],"propose":[111],"an":[112,116,152],"index":[114,148,195,203,230,232],"explicit":[117],"two-stage":[118],"design":[119,185],"combining":[120],"fast":[122],"filter":[123],"stage":[124,132],"highly":[126],"compressed":[127],"vectors":[128],"refine":[131],"ensure":[134],"recall,":[135],"devise":[138],"novel":[140],"lightweight":[141],"machine":[142],"technique":[144],"fine-tune":[146],"parameters.":[149,182],"We":[150,200],"introduce":[151],"early":[153],"termination":[154],"check":[155],"dynamically":[157],"adapt":[158],"process":[161],"each":[163],"query.":[164],"Next,":[165],"add":[167],"support":[168],"writes":[170],"while":[171],"maintaining":[172],"performance":[174],"decoupling":[176],"management":[178],"learned":[181],"Finally,":[183],"HAKES,":[186],"distributed":[188,212],"serves":[192],"new":[194],"disaggregated":[198],"architecture.":[199],"evaluate":[201],"our":[202,229],"system":[205],"against":[206],"12":[207],"state-of-the-art":[208],"three":[211],"databases,":[214],"using":[215],"datasets":[218],"generated":[219],"models.":[223],"The":[224],"experimental":[225],"results":[226],"show":[227],"outperforms":[231],"baselines":[233],"region":[238],"Furthermore,":[244],"HAKES":[245],"scalable":[247],"up":[250],"16x":[252],"higher":[253],"throughputs":[254],"than":[255],"baselines.":[257]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-09-04T00:00:00"}