{"id":"https://openalex.org/W4412394907","doi":"https://doi.org/10.1145/3726302.3729996","title":"Highly Efficient Disk-based Nearest Neighbor Search on Extended Neighborhood Graph","display_name":"Highly Efficient Disk-based Nearest Neighbor Search on Extended Neighborhood Graph","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412394907","doi":"https://doi.org/10.1145/3726302.3729996"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3729996","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3729996","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729996","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729996","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Cheng Zhang","orcid":"https://orcid.org/0009-0000-0110-3309"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Cheng Zhang","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0000-0110-3309","affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianzhi Wang","orcid":"https://orcid.org/0009-0005-9644-7249"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzhi Wang","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0005-9644-7249","affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101660306","display_name":"Wan\u2010Lei Zhao","orcid":"https://orcid.org/0000-0002-7915-447X"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wan-Lei Zhao","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-7915-447X","affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034442678","display_name":"Shihai Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shihai Xiao","raw_affiliation_strings":["Huawei Technologies Co., Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-0658-9843","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Hangzhou, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13991403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2513","last_page":"2523"},"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":0.9997000098228455,"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":0.9997000098228455,"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/T11106","display_name":"Data Management and Algorithms","score":0.9995999932289124,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9975000023841858,"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/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.7446741461753845},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6685014367103577},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.6524719595909119},{"id":"https://openalex.org/keywords/nearest-neighbor-graph","display_name":"Nearest neighbor graph","score":0.6213284134864807},{"id":"https://openalex.org/keywords/best-bin-first","display_name":"Best bin first","score":0.5853895545005798},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5092031359672546},{"id":"https://openalex.org/keywords/nearest-neighbor-chain-algorithm","display_name":"Nearest-neighbor chain algorithm","score":0.4272048771381378},{"id":"https://openalex.org/keywords/large-margin-nearest-neighbor","display_name":"Large margin nearest neighbor","score":0.41693365573883057},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36337968707084656},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2692045569419861},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2637133002281189},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.1867077350616455}],"concepts":[{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.7446741461753845},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6685014367103577},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.6524719595909119},{"id":"https://openalex.org/C90988772","wikidata":"https://www.wikidata.org/wiki/Q2855103","display_name":"Nearest neighbor graph","level":3,"score":0.6213284134864807},{"id":"https://openalex.org/C161986146","wikidata":"https://www.wikidata.org/wiki/Q4896845","display_name":"Best bin first","level":3,"score":0.5853895545005798},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5092031359672546},{"id":"https://openalex.org/C102164700","wikidata":"https://www.wikidata.org/wiki/Q17162702","display_name":"Nearest-neighbor chain algorithm","level":5,"score":0.4272048771381378},{"id":"https://openalex.org/C94475309","wikidata":"https://www.wikidata.org/wiki/Q6489154","display_name":"Large margin nearest neighbor","level":3,"score":0.41693365573883057},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36337968707084656},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2692045569419861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2637133002281189},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.1867077350616455},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.0},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3726302.3729996","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3729996","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729996","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3726302.3729996","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3729996","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729996","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4972156769","display_name":null,"funder_award_id":"61972326","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412394907.pdf","grobid_xml":"https://content.openalex.org/works/W4412394907.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1536741282","https://openalex.org/W2010642153","https://openalex.org/W2042281163","https://openalex.org/W2086504823","https://openalex.org/W2110026675","https://openalex.org/W2111006384","https://openalex.org/W2124509324","https://openalex.org/W2144679084","https://openalex.org/W2147717514","https://openalex.org/W2151103935","https://openalex.org/W2151135734","https://openalex.org/W2165558283","https://openalex.org/W2299467264","https://openalex.org/W2427312773","https://openalex.org/W2511638354","https://openalex.org/W2602753196","https://openalex.org/W2906270115","https://openalex.org/W2960484119","https://openalex.org/W2963265099","https://openalex.org/W2963284996","https://openalex.org/W2963469388","https://openalex.org/W2990138404","https://openalex.org/W2996499210","https://openalex.org/W3004954215","https://openalex.org/W3136183693","https://openalex.org/W3156129346","https://openalex.org/W3196481040","https://openalex.org/W4236965008","https://openalex.org/W4367046898","https://openalex.org/W4367047226","https://openalex.org/W4368755247","https://openalex.org/W4380433185","https://openalex.org/W4385568335","https://openalex.org/W4387321071","https://openalex.org/W4387968104","https://openalex.org/W4390647563","https://openalex.org/W4399175194","https://openalex.org/W4400528059","https://openalex.org/W4400528326","https://openalex.org/W4401857375"],"related_works":["https://openalex.org/W2182477562","https://openalex.org/W2795392346","https://openalex.org/W2969538544","https://openalex.org/W2351157934","https://openalex.org/W4246757943","https://openalex.org/W2375128115","https://openalex.org/W1595303882","https://openalex.org/W2085998272","https://openalex.org/W1558159560","https://openalex.org/W2148008870"],"abstract_inverted_index":{"Nearest":[0],"neighbor":[1],"search":[2,17,43,68,119,155,185],"(NN":[3],"search)":[4],"plays":[5],"a":[6,59,122,147],"fundamental":[7],"role":[8],"in":[9,44,55,115,137,146],"many":[10],"disciplines.":[11],"According":[12],"to":[13,29,83,132,164],"recent":[14],"studies,":[15],"graph-based":[16],"methods":[18],"show":[19],"superior":[20],"performance":[21],"over":[22],"other":[23],"types":[24],"of":[25,90,100,109,178],"methods.":[26,189],"In":[27,81],"order":[28],"accommodate":[30],"the":[31,37,40,46,50,65,84,88,91,101,107,118,134,140,165,171,176],"high":[32,203],"dimensionality":[33],"as":[34,36,202,204],"well":[35],"growing":[38],"data-scale,":[39],"disk-based":[41,66],"NN":[42,67,112,154],"which":[45,114],"index":[47,86],"graph":[48,92,135],"and":[49],"full-precision":[51],"vectors":[52],"are":[53,94],"kept":[54],"SSD":[56],"has":[57],"become":[58],"promising":[60],"direction.":[61],"This":[62],"paper":[63],"optimizes":[64],"from":[69,96],"three":[70],"perspectives.":[71],"Firstly,":[72],"an":[73,151],"eXtended":[74],"Neighborhood":[75],"Graph":[76],"(XN-Graph)":[77],"structure":[78],"is":[79,130,161,195,201],"proposed.":[80,162],"contrast":[82],"existing":[85,166],"graphs,":[87],"out-edges":[89],"neighborhood":[93],"collected":[95],"much":[97],"wider":[98],"coverage":[99],"data":[102],"space.":[103],"It":[104],"therefore":[105],"reduces":[106,117,170],"number":[108],"hops":[110],"during":[111],"search,":[113],"turn":[116],"latency.":[120],"Additionally,":[121],"dataset":[123],"partitioning":[124],"method":[125,156],"called":[126,157],"Boundary-adaptive":[127],"Balanced":[128],"Partition":[129],"proposed":[131],"facilitate":[133],"construction":[136],"cases":[138],"where":[139],"system":[141],"cannot":[142],"handle":[143],"large":[144],"datasets":[145],"single":[148],"round.":[149],"Moreover,":[150],"efficient":[152],"hybrid":[153],"In-Memory":[158],"First":[159],"Search":[160],"Compared":[163],"methods,":[167],"it":[168,180],"considerably":[169],"CPU":[172],"idle":[173],"times.":[174],"With":[175],"support":[177],"XN-Graph,":[179],"shows":[181],"1.5-3":[182],"times":[183],"lower":[184],"latency":[186],"than":[187],"SOTA":[188],"On":[190],"billion-scale":[191],"datasets,":[192],"its":[193],"QPS":[194],"still":[196],"above":[197],"4000":[198],"when":[199],"Recall@10":[200],"0.9.":[205]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}