{"id":"https://openalex.org/W7131275595","doi":"https://doi.org/10.1109/tkde.2026.3667997","title":"Geometric Partition for Billion-Scale Approximate Nearest Neighbor Search","display_name":"Geometric Partition for Billion-Scale Approximate Nearest Neighbor Search","publication_year":2026,"publication_date":"2026-02-24","ids":{"openalex":"https://openalex.org/W7131275595","doi":"https://doi.org/10.1109/tkde.2026.3667997"},"language":null,"primary_location":{"id":"doi:10.1109/tkde.2026.3667997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2026.3667997","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","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/A5017240878","display_name":"Yujian Fu","orcid":"https://orcid.org/0009-0006-9256-295X"},"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":"Yujian Fu","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0006-9256-295X","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126683920","display_name":"Cheng Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng Chen","raw_affiliation_strings":["ByteDance, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yao Chen","orcid":"https://orcid.org/0000-0002-4281-2053"},"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":"Yao Chen","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4281-2053","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Weng-Fai Wong","orcid":"https://orcid.org/0000-0002-5798-2282"},"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":"Weng-Fai Wong","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-5798-2282","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121089036","display_name":"Bingsheng He","orcid":null},"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":"Bingsheng He","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-8618-4581","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"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":0.24108568,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":"5","first_page":"2865","last_page":"2879"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.3197999894618988,"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":0.3197999894618988,"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/T10996","display_name":"Computational Geometry and Mesh Generation","score":0.15060000121593475,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.08020000159740448,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/search-engine-indexing","display_name":"Search engine indexing","score":0.6812000274658203},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.5996999740600586},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5559999942779541},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5286999940872192},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.4991999864578247},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4214000105857849},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.40790000557899475},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4052000045776367},{"id":"https://openalex.org/keywords/range-query","display_name":"Range query (database)","score":0.38920000195503235},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.38850000500679016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6980000138282776},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6812000274658203},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.5996999740600586},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5559999942779541},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5286999940872192},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.4991999864578247},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42579999566078186},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4214000105857849},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4052000045776367},{"id":"https://openalex.org/C136736807","wikidata":"https://www.wikidata.org/wiki/Q818943","display_name":"Range query (database)","level":5,"score":0.38920000195503235},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3747999966144562},{"id":"https://openalex.org/C56435381","wikidata":"https://www.wikidata.org/wiki/Q1196371","display_name":"Geometric transformation","level":3,"score":0.35569998621940613},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C7305733","wikidata":"https://www.wikidata.org/wiki/Q207961","display_name":"Geometric shape","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C13336665","wikidata":"https://www.wikidata.org/wiki/Q125977","display_name":"Vector space","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29490000009536743},{"id":"https://openalex.org/C2639959","wikidata":"https://www.wikidata.org/wiki/Q1344778","display_name":"Distance measures","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C59276292","wikidata":"https://www.wikidata.org/wiki/Q580427","display_name":"Database index","level":3,"score":0.29010000824928284},{"id":"https://openalex.org/C13670688","wikidata":"https://www.wikidata.org/wiki/Q3500548","display_name":"Space partitioning","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C29123130","wikidata":"https://www.wikidata.org/wiki/Q874709","display_name":"Computational geometry","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C53661774","wikidata":"https://www.wikidata.org/wiki/Q13108095","display_name":"Cover tree","level":5,"score":0.267300009727478},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2653999924659729},{"id":"https://openalex.org/C111208986","wikidata":"https://www.wikidata.org/wiki/Q901698","display_name":"Distance matrix","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2026.3667997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2026.3667997","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large-scale":[0],"approximate":[1],"nearest":[2],"neighbor":[3],"search":[4,53,204],"(ANNS)":[5],"has":[6],"become":[7],"a":[8,12,30,90,104,143,213],"fundamental":[9],"operation":[10],"in":[11],"wide":[13],"range":[14],"of":[15,62,68,76,93,137,186,215],"modern":[16],"applications,":[17],"including":[18],"recommendation":[19],"systems":[20],"and":[21,87,121,169,176],"large":[22,60,91],"language":[23],"models.":[24],"Partition-based":[25],"indexes":[26],"have":[27],"emerged":[28],"as":[29,38,166],"popular":[31],"solution":[32],"for":[33,41,73,85,146],"billion-scale":[34,56,180],"ANNS":[35,43],"tasks,":[36],"serving":[37],"the":[39,77,119,135,184],"basis":[40],"many":[42],"approaches.":[44],"However,":[45],"our":[46,187],"analysis":[47,175],"indicates":[48],"that,":[49],"to":[50,114,225,237],"achieve":[51],"optimal":[52],"performance":[54],"on":[55,81,179,203],"datasets,":[57,181],"an":[58],"extremely":[59],"number":[61,92],"partitions":[63,94,149],"(tens":[64],"or":[65,127,232],"even":[66],"hundreds":[67],"millions)":[69],"is":[70],"often":[71],"required":[72],"fine-grained":[74],"partitioning":[75],"feature":[78],"space.":[79],"Relying":[80],"full-precision":[82,138],"distance":[83,107,116,129,154],"calculations":[84],"constructing":[86],"querying":[88],"such":[89,165],"imposes":[95],"significant":[96],"time":[97],"costs.":[98],"In":[99,206],"this":[100,131,152],"work,":[101],"we":[102,182],"propose":[103],"novel":[105],"geometric":[106,112,153,188],"inference":[108],"mechanism":[109],"that":[110,150,195],"leverages":[111],"relationships":[113],"expedite":[115],"computations":[117],"between":[118],"vector":[120,167],"space":[122,148],"partitions.":[123],"By":[124],"reusing":[125],"intermediate":[126],"offline-computed":[128],"information,":[130],"method":[132],"substantially":[133],"reduces":[134],"overhead":[136],"calculations.":[139],"We":[140],"also":[141,229],"introduce":[142],"clustering":[144],"paradigm":[145],"generating":[147],"incorporates":[151],"pattern,":[155],"which":[156],"can":[157],"be":[158],"seamlessly":[159],"integrated":[160],"with":[161],"other":[162],"indexing":[163],"schemes":[164],"quantization":[168],"proximity":[170],"graphs.":[171],"Through":[172],"detailed":[173],"complexity":[174],"extensive":[177],"experiments":[178],"confirm":[183],"efficiency":[185],"index":[189],"(GI)":[190],"design.":[191],"Empirical":[192],"results":[193],"show":[194],"GI-based":[196],"solutions":[197],"consistently":[198],"surpass":[199],"various":[200],"baseline":[201],"methods":[202],"efficiency.":[205],"particular,":[207],"they":[208],"offer":[209],"considerable":[210],"acceleration":[211],"(exceeding":[212],"factor":[214],"2.0)":[216],"at":[217],"high":[218],"recall":[219],"levels":[220],"(e.g.,":[221],"Recall10@10":[222],"=":[223],"95%)":[224],"partition-based":[226],"solutions,":[227],"while":[228],"demonstrating":[230],"comparable":[231],"superior":[233],"query":[234],"throughput":[235],"relative":[236],"leading":[238],"graph-based":[239],"indexes.":[240]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-25T00:00:00"}