{"id":"https://openalex.org/W4414241804","doi":"https://doi.org/10.14778/3750601.3750619","title":"GaussDB-Vector: A Large-Scale Persistent Real-Time Vector Database for LLM Applications","display_name":"GaussDB-Vector: A Large-Scale Persistent Real-Time Vector Database for LLM Applications","publication_year":2025,"publication_date":"2025-08-01","ids":{"openalex":"https://openalex.org/W4414241804","doi":"https://doi.org/10.14778/3750601.3750619"},"language":"en","primary_location":{"id":"doi:10.14778/3750601.3750619","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3750601.3750619","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":["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/A5101588053","display_name":"Ji Sun","orcid":"https://orcid.org/0000-0002-9782-7201"},"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":"Ji Sun","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119268361","display_name":"Guoliang Li","orcid":"https://orcid.org/0009-0007-8430-5141"},"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108368538","display_name":"James Pan","orcid":null},"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":"James Pan","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351617","display_name":"Jiang Wang","orcid":"https://orcid.org/0000-0002-3871-598X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang Wang","raw_affiliation_strings":["Huawei"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yongqing Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongqing Xie","raw_affiliation_strings":["Huawei"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004266970","display_name":"Ruicheng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruicheng Liu","raw_affiliation_strings":["Huawei"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041199382","display_name":"Wen Nie","orcid":"https://orcid.org/0000-0002-3088-0470"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen Nie","raw_affiliation_strings":["Huawei"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5932,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.95341949,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"18","issue":"12","first_page":"4951","last_page":"4963"},"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":0.9939000010490417,"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":0.9939000010490417,"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/T11269","display_name":"Algorithms and Data Compression","score":0.982200026512146,"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/T11106","display_name":"Data Management and Algorithms","score":0.9761999845504761,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7105000019073486},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3537999987602234},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.35359999537467957},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.3416000008583069},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.3228999972343445},{"id":"https://openalex.org/keywords/distributed-database","display_name":"Distributed database","score":0.31520000100135803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7825000286102295},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7105000019073486},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.47780001163482666},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4675000011920929},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36730000376701355},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3537999987602234},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3750601.3750619","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3750601.3750619","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1566135517","https://openalex.org/W1967005434","https://openalex.org/W2038044292","https://openalex.org/W2068739275","https://openalex.org/W2124509324","https://openalex.org/W2147717514","https://openalex.org/W2151103935","https://openalex.org/W2913059114","https://openalex.org/W2963284996","https://openalex.org/W2963469388","https://openalex.org/W3196481040","https://openalex.org/W4245145882","https://openalex.org/W4249914127","https://openalex.org/W4298468057","https://openalex.org/W4389519218","https://openalex.org/W4404181049"],"related_works":[],"abstract_inverted_index":{"Vector":[0],"databases":[1,30],"are":[2,89],"widely":[3],"used":[4],"as":[5],"a":[6,60,99,154],"fundamental":[7],"tool":[8],"for":[9,98,104],"addressing":[10],"the":[11,22,48],"weaknesses":[12],"of":[13,25,50,156],"large":[14],"language":[15],"model":[16],"(LLM)":[17],"applications,":[18],"specifically":[19],"hallucinations":[20],"and":[21,74,81,107,113,131,137],"high":[23,76],"cost":[24,49],"inference.":[26],"However,":[27],"existing":[28],"vector":[29,64,101],"either":[31],"cater":[32],"to":[33,120,141,158],"niche":[34],"applications":[35],"with":[36],"low-latency":[37,69],"in-memory":[38],"search,":[39,71,80,130],"or":[40],"offer":[41],"sophisticated":[42],"data":[43],"management":[44],"capabilities":[45],"but":[46],"at":[47],"low":[51],"performance.":[52],"To":[53],"address":[54],"these":[55],"limitations,":[56],"we":[57],"propose":[58],"GaussDB-Vector,":[59],"high-performance,":[61],"real-time":[62,72],"persistent":[63],"database":[65],"that":[66,148],"excels":[67],"in":[68,139],"scalable":[70],"inserts":[73],"deletes,":[75],"availability,":[77],"large-scale":[78],"distributed":[79],"hybrid":[82],"scalar-vector":[83],"filtered":[84],"search":[85],"capabilities.":[86],"These":[87],"features":[88],"primarily":[90],"achieved":[91],"through":[92],"an":[93],"innovative":[94],"storage":[95],"architecture":[96],"designed":[97],"graph-based":[100],"index,":[102],"optimized":[103],"I/O":[105,123],"operations":[106],"adaptable":[108],"across":[109],"various":[110],"dataset":[111],"sizes":[112],"dimensions,":[114],"complemented":[115],"by":[116,153],"novel":[117],"buffering":[118],"strategies":[119],"further":[121,142],"reduce":[122],"burdens.":[124],"GaussDB-Vector":[125,149],"supports":[126],"product":[127],"quantization,":[128],"parallel":[129],"hardware":[132],"acceleration":[133],"via":[134],"SIMD,":[135],"GPUs,":[136],"NPUs":[138],"order":[140],"accelerate":[143],"queries.":[144],"Experimental":[145],"results":[146],"show":[147],"outperforms":[150],"competitive":[151],"baselines":[152],"factor":[155],"1":[157],"5":[159],"times.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":6}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
