{"id":"https://openalex.org/W4413755895","doi":"https://doi.org/10.14778/3718057.3718078","title":"BigVectorBench: Heterogeneous Data Embedding and Compound Queries are Essential in Evaluating Vector Databases","display_name":"BigVectorBench: Heterogeneous Data Embedding and Compound Queries are Essential in Evaluating Vector Databases","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4413755895","doi":"https://doi.org/10.14778/3718057.3718078"},"language":"en","primary_location":{"id":"doi:10.14778/3718057.3718078","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3718057.3718078","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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/A5113986498","display_name":"Guoxin Kang","orcid":"https://orcid.org/0000-0002-5180-7053"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guoxin Kang","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101196299","display_name":"Zhongxin Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongxin Ge","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016212887","display_name":"Jingpei Hu","orcid":"https://orcid.org/0000-0002-1362-0909"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingpei Hu","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060274220","display_name":"Xueya Zhang","orcid":"https://orcid.org/0000-0001-7844-4689"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueya Zhang","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100435763","display_name":"Lei Wang","orcid":"https://orcid.org/0000-0001-7103-9402"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Wang","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085963553","display_name":"Jianfeng Zhan","orcid":"https://orcid.org/0000-0002-3728-6837"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Zhan","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5113986498"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27306741,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"5","first_page":"1536","last_page":"1550"},"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":0.9994000196456909,"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":0.9994000196456909,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9968000054359436,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9951000213623047,"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/database","display_name":"Database","score":0.6373958587646484},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.635502815246582},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5701441168785095},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45893996953964233},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.400200754404068},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11538398265838623}],"concepts":[{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6373958587646484},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.635502815246582},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5701441168785095},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45893996953964233},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.400200754404068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11538398265838623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3718057.3718078","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3718057.3718078","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W136016496","https://openalex.org/W1536112217","https://openalex.org/W1583837637","https://openalex.org/W1634005169","https://openalex.org/W1997944350","https://openalex.org/W2058292646","https://openalex.org/W2069065514","https://openalex.org/W2086179657","https://openalex.org/W2086504823","https://openalex.org/W2097921974","https://openalex.org/W2124509324","https://openalex.org/W2150593711","https://openalex.org/W2750779823","https://openalex.org/W2781528640","https://openalex.org/W2790634852","https://openalex.org/W2911708124","https://openalex.org/W2912355851","https://openalex.org/W2914304175","https://openalex.org/W2930957955","https://openalex.org/W2949985202","https://openalex.org/W2950128007","https://openalex.org/W2963265099","https://openalex.org/W2963315828","https://openalex.org/W2963469388","https://openalex.org/W2998702515","https://openalex.org/W4205244689","https://openalex.org/W4236965008","https://openalex.org/W4239019441","https://openalex.org/W4244017338","https://openalex.org/W4247028386","https://openalex.org/W4285451014","https://openalex.org/W4312285477","https://openalex.org/W4327909698","https://openalex.org/W4387078920","https://openalex.org/W4392827985","https://openalex.org/W4396506980","https://openalex.org/W4400641571","https://openalex.org/W4404181035"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2081900870","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Vector":[0],"databases":[1,29],"are":[2,136,170],"designed":[3,112],"to":[4,113],"effectively":[5],"store,":[6],"organize,":[7],"and":[8,14,18,39,91,122,156,167],"retrieve":[9],"high-dimensional":[10],"vectors,":[11],"enabling":[12],"faster":[13],"more":[15],"accurate":[16],"querying":[17],"analysis.":[19],"This":[20],"study":[21],"highlights":[22],"that":[23],"the":[24,58,124,150],"performance":[25,126,158],"of":[26,127,154,160],"cutting-edge":[27],"vector":[28,55,84,99,115,144,162],"hinges":[30],"on":[31],"their":[32],"proficiency":[33],"in":[34,97,139],"managing":[35],"heterogeneous":[36,88,128],"data":[37,50,89],"embedding":[38,90,125],"handling":[40],"compound":[41,92,133],"queries.":[42],"The":[43,69],"former":[44],"task":[45],"revolves":[46],"around":[47],"converting":[48],"varied":[49],"types":[51],"into":[52],"a":[53,95,109],"cohesive":[54],"format,":[56],"while":[57],"latter":[59],"involves":[60],"processing":[61],"multimodal":[62],"or":[63],"single-modal":[64],"queries":[65],"with":[66],"precise":[67],"constraints.":[68],"paper":[70],"advocates":[71],"for":[72],"evaluating":[73,98,123],"these":[74],"dual":[75],"tasks":[76],"within":[77],"an":[78],"integrated":[79],"benchmark":[80,110],"framework.":[81],"However,":[82],"state-of-the-art":[83],"database":[85,100,116],"benchmarks":[86],"overlook":[87],"queries,":[93,134],"creating":[94],"gap":[96],"performance.":[101,117],"To":[102],"address":[103],"this":[104],"gap,":[105],"we":[106],"introduce":[107],"BigVectorBench,":[108],"suite":[111],"evaluate":[114],"BigVectorBench":[118,155],"contributes":[119],"by":[120],"defining":[121],"data.":[129],"Additionally,":[130],"it":[131],"abstracts":[132],"which":[135],"increasingly":[137],"used":[138],"real-world":[140],"applications,":[141],"replacing":[142],"unimodal":[143],"searches.":[145],"Our":[146],"rigorous":[147],"evaluations":[148],"validate":[149],"two":[151],"design":[152],"decisions":[153],"identify":[157],"bottlenecks":[159],"mainstream":[161],"databases.":[163],"Its":[164],"source":[165],"code":[166],"user":[168],"manual":[169],"available":[171],"from":[172],"https://github.com/BenchCouncil/BigVectorBench.":[173]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
