{"id":"https://openalex.org/W4417070502","doi":"https://doi.org/10.1145/3769763","title":"Attribute Filtering in Approximate Nearest Neighbor Search: An In-depth Experimental Study","display_name":"Attribute Filtering in Approximate Nearest Neighbor Search: An In-depth Experimental Study","publication_year":2025,"publication_date":"2025-12-04","ids":{"openalex":"https://openalex.org/W4417070502","doi":"https://doi.org/10.1145/3769763"},"language":"en","primary_location":{"id":"doi:10.1145/3769763","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3769763","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":["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/A5091485940","display_name":"Li Mocheng","orcid":"https://orcid.org/0000-0002-5524-1042"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mocheng Li","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-5524-1042","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100367774","display_name":"Xiao Yan","orcid":"https://orcid.org/0000-0002-2122-915X"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210111616","display_name":"Wuhan Business University","ror":"https://ror.org/0282ggx30","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210111616"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Yan","raw_affiliation_strings":["Wuhan University, Institute for Math & AI, Wuhan, Wuhan, Hubei, China"],"raw_orcid":"https://orcid.org/0000-0002-2122-915X","affiliations":[{"raw_affiliation_string":"Wuhan University, Institute for Math & AI, Wuhan, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4210111616"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038360007","display_name":"Baotong Lu","orcid":"https://orcid.org/0000-0002-0230-1048"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baotong Lu","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0230-1048","affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yue Zhang","orcid":"https://orcid.org/0009-0009-5199-7799"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Zhang","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0009-5199-7799","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016082884","display_name":"James Cheng","orcid":"https://orcid.org/0000-0001-6313-6288"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"James Cheng","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-6313-6288","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055857919","display_name":"Chenhao Ma","orcid":"https://orcid.org/0000-0002-3243-8512"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenhao Ma","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-3243-8512","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40805091,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":"6","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.6718999743461609,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.6718999743461609,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.05739999935030937,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.04879999905824661,"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/pruning","display_name":"Pruning","score":0.6395999789237976},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.612500011920929},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4580000042915344},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.4302999973297119},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.40959998965263367},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.40869998931884766},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.40610000491142273},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.4007999897003174},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.38260000944137573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7305999994277954},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.699400007724762},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6395999789237976},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.612500011920929},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4580000042915344},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.4302999973297119},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4277999997138977},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.40959998965263367},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.40869998931884766},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.40610000491142273},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.4007999897003174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.391400009393692},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.376800000667572},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.35690000653266907},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.2676999866962433},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3769763","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3769763","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1392884172","display_name":null,"funder_award_id":"62302421","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320318398","display_name":"Ant Group","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1965680834","https://openalex.org/W2086179657","https://openalex.org/W2099253838","https://openalex.org/W2101562895","https://openalex.org/W2110026675","https://openalex.org/W2122111042","https://openalex.org/W2132234208","https://openalex.org/W2162006472","https://openalex.org/W2742272831","https://openalex.org/W2887218294","https://openalex.org/W2901613577","https://openalex.org/W2949985202","https://openalex.org/W2963265099","https://openalex.org/W2996499210","https://openalex.org/W3010856967","https://openalex.org/W3011056378","https://openalex.org/W3029865833","https://openalex.org/W3037277842","https://openalex.org/W3085011441","https://openalex.org/W4367046898","https://openalex.org/W4380887855","https://openalex.org/W4381329135","https://openalex.org/W4393183654","https://openalex.org/W4399174383","https://openalex.org/W4399175194","https://openalex.org/W4400641571","https://openalex.org/W4405623356"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,93,185,205],"growing":[2],"integration":[3],"of":[4,38,55,109,187,209],"structured":[5,21],"and":[6,47,59,76,96,118,132,140,152,168,171,192,207,219],"unstructured":[7],"data,":[8],"new":[9],"methods":[10,58,154],"have":[11,41],"emerged":[12],"for":[13,67,215,223],"performing":[14],"similarity":[15],"searches":[16],"on":[17,115,149,196,200],"vectors":[18],"while":[19],"honoring":[20],"attribute":[22,116],"constraints,":[23],"i.e.,":[24,127],"a":[25,53,64,68,85,106,145],"process":[26],"known":[27],"as":[28],"Filtering":[29,87,111],"Approximate":[30],"Nearest":[31],"Neighbor":[32],"(Filtering":[33],"ANN)":[34],"search.":[35],"Since":[36],"many":[37],"these":[39],"algorithms":[40,95,113,151],"only":[42],"appeared":[43],"in":[44],"recent":[45],"years":[46],"are":[48],"designed":[49],"to":[50,136,161,177],"work":[51],"with":[52,159],"variety":[54],"base":[56],"indexing":[57],"filtering":[60,119,194],"strategies,":[61,131],"there":[62],"is":[63,228],"pressing":[65],"need":[66],"unified":[69,86],"analysis":[70,183],"that":[71,91],"identifies":[72],"their":[73,124],"core":[74],"techniques":[75],"enables":[77],"meaningful":[78],"comparisons.":[79],"In":[80],"this":[81],"work,":[82],"we":[83,104,122,203],"present":[84],"ANN":[88,112],"search":[89],"interface":[90],"encompasses":[92],"latest":[94],"evaluate":[97],"them":[98],"extensively":[99],"from":[100,175],"multiple":[101],"perspectives.":[102],"First,":[103],"propose":[105],"comprehensive":[107],"taxonomy":[108],"existing":[110],"based":[114],"types":[117],"strategies.":[120],"Next,":[121],"analyze":[123],"key":[125],"components,":[126],"index":[128],"structures,":[129],"pruning":[130],"entry":[133,189],"point":[134,190],"selection,":[135,191],"elucidate":[137],"design":[138],"differences":[139],"tradeoffs.":[141],"We":[142],"then":[143],"conduct":[144],"broad":[146],"experimental":[147],"evaluation":[148],"10":[150,162],"12":[153],"across":[155],"4":[156],"datasets":[157],"(each":[158],"up":[160],"million":[163],"items),":[164],"incorporating":[165],"both":[166],"synthetic":[167],"real":[169],"attributes":[170],"covering":[172],"selectivity":[173],"levels":[174],"0.1%":[176],"100%.":[178],"Finally,":[179],"an":[180],"in-depth":[181],"component":[182],"reveals":[184],"influence":[186],"pruning,":[188],"edge":[193],"costs":[195],"overall":[197],"performance.":[198],"Based":[199],"our":[201],"findings,":[202],"summarize":[204],"strengths":[206],"limitations":[208],"each":[210],"approach,":[211],"provide":[212],"practical":[213],"guidelines":[214],"selecting":[216],"appropriate":[217],"methods,":[218],"suggest":[220],"promising":[221],"directions":[222],"future":[224],"research.":[225],"Our":[226],"code":[227],"available":[229],"at:":[230],"https://github.com/lmccccc/FANNBench.":[231]},"counts_by_year":[],"updated_date":"2026-06-14T06:11:07.267592","created_date":"2025-12-06T00:00:00"}