{"id":"https://openalex.org/W3032267619","doi":"https://doi.org/10.1145/3375395.3387649","title":"On the I/O Complexity of the k-Nearest Neighbors Problem","display_name":"On the I/O Complexity of the k-Nearest Neighbors Problem","publication_year":2020,"publication_date":"2020-05-29","ids":{"openalex":"https://openalex.org/W3032267619","doi":"https://doi.org/10.1145/3375395.3387649","mag":"3032267619"},"language":"en","primary_location":{"id":"doi:10.1145/3375395.3387649","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3375395.3387649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.itu.dk/portal/da/publications/261aa4d2-051e-49bf-b9ab-336e3b73ff14","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080620426","display_name":"Mayank Goswami","orcid":"https://orcid.org/0000-0001-8829-9980"},"institutions":[{"id":"https://openalex.org/I111455621","display_name":"Queens College, CUNY","ror":"https://ror.org/03v8adn41","country_code":"US","type":"education","lineage":["https://openalex.org/I111455621"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mayank Goswami","raw_affiliation_strings":["Queens College CUNY, Flushing, NY, USA"],"affiliations":[{"raw_affiliation_string":"Queens College CUNY, Flushing, NY, USA","institution_ids":["https://openalex.org/I111455621"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072095949","display_name":"Riko Jacob","orcid":"https://orcid.org/0000-0001-9470-1809"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Riko Jacob","raw_affiliation_strings":["IT University of Copenhagen, K\u00f8benhavn S, Denmark"],"affiliations":[{"raw_affiliation_string":"IT University of Copenhagen, K\u00f8benhavn S, Denmark","institution_ids":["https://openalex.org/I83467386"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014293815","display_name":"Rasmus Pagh","orcid":"https://orcid.org/0000-0002-1516-9306"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Rasmus Pagh","raw_affiliation_strings":["BARC and IT University of Copenhagen, K\u00f8benhavn S, Denmark"],"affiliations":[{"raw_affiliation_string":"BARC and IT University of Copenhagen, K\u00f8benhavn S, Denmark","institution_ids":["https://openalex.org/I83467386"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5080620426"],"corresponding_institution_ids":["https://openalex.org/I111455621"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.0891181,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"70","issue":null,"first_page":"205","last_page":"212"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10720","display_name":"Complexity and Algorithms in Graphs","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T10720","display_name":"Complexity and Algorithms in Graphs","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9979000091552734,"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":0.9970999956130981,"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/combinatorics","display_name":"Combinatorics","score":0.6298130750656128},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.5861705541610718},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.580153226852417},{"id":"https://openalex.org/keywords/hamming-distance","display_name":"Hamming distance","score":0.5672107934951782},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.5663734078407288},{"id":"https://openalex.org/keywords/metric-space","display_name":"Metric space","score":0.5406733155250549},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5390602350234985},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5348585844039917},{"id":"https://openalex.org/keywords/hamming-space","display_name":"Hamming space","score":0.5330266952514648},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5172498822212219},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5089285373687744},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.5077882409095764},{"id":"https://openalex.org/keywords/approximation-algorithm","display_name":"Approximation algorithm","score":0.49283456802368164},{"id":"https://openalex.org/keywords/linear-space","display_name":"Linear space","score":0.472713440656662},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.4276910424232483},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33926495909690857},{"id":"https://openalex.org/keywords/hamming-code","display_name":"Hamming code","score":0.29148030281066895},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.20026013255119324}],"concepts":[{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.6298130750656128},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.5861705541610718},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.580153226852417},{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.5672107934951782},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5663734078407288},{"id":"https://openalex.org/C198043062","wikidata":"https://www.wikidata.org/wiki/Q180953","display_name":"Metric space","level":2,"score":0.5406733155250549},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5390602350234985},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5348585844039917},{"id":"https://openalex.org/C2779494224","wikidata":"https://www.wikidata.org/wiki/Q5645799","display_name":"Hamming space","level":5,"score":0.5330266952514648},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5172498822212219},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5089285373687744},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.5077882409095764},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.49283456802368164},{"id":"https://openalex.org/C176370821","wikidata":"https://www.wikidata.org/wiki/Q1826459","display_name":"Linear space","level":2,"score":0.472713440656662},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.4276910424232483},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33926495909690857},{"id":"https://openalex.org/C73150493","wikidata":"https://www.wikidata.org/wiki/Q853922","display_name":"Hamming code","level":4,"score":0.29148030281066895},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.20026013255119324},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C157125643","wikidata":"https://www.wikidata.org/wiki/Q884707","display_name":"Block code","level":3,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3375395.3387649","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3375395.3387649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire/261aa4d2-051e-49bf-b9ab-336e3b73ff14","is_oa":true,"landing_page_url":"https://pure.itu.dk/portal/da/publications/261aa4d2-051e-49bf-b9ab-336e3b73ff14","pdf_url":null,"source":{"id":"https://openalex.org/S4377196680","display_name":"IT University Of Copenhagen (IT University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83467386","host_organization_name":"IT University of Copenhagen","host_organization_lineage":["https://openalex.org/I83467386"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Goswami, M, Jacob, R & Pagh, R 2020, On the I/O Complexity of the k-Nearest Neighbors Problem. in PODS'20: Proceedings of the 39th ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems. Association for Computing Machinery, ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems, pp. 205-212. https://doi.org/10.1145/3375395.3387649","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/261aa4d2-051e-49bf-b9ab-336e3b73ff14","is_oa":true,"landing_page_url":"https://pure.itu.dk/portal/da/publications/261aa4d2-051e-49bf-b9ab-336e3b73ff14","pdf_url":null,"source":{"id":"https://openalex.org/S4377196680","display_name":"IT University Of Copenhagen (IT University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83467386","host_organization_name":"IT University of Copenhagen","host_organization_lineage":["https://openalex.org/I83467386"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Goswami, M, Jacob, R & Pagh, R 2020, On the I/O Complexity of the k-Nearest Neighbors Problem. in PODS'20: Proceedings of the 39th ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems. Association for Computing Machinery, ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems, pp. 205-212. https://doi.org/10.1145/3375395.3387649","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G4422840520","display_name":null,"funder_award_id":"16582","funder_id":"https://openalex.org/F4320310490","funder_display_name":"Villum Fonden"},{"id":"https://openalex.org/G563750942","display_name":null,"funder_award_id":"CRII-1755791 and CCF-1910873","funder_id":"https://openalex.org/F4320315254","funder_display_name":"Innovative Research Group Project of the National Natural Science Foundation of China"},{"id":"https://openalex.org/G6159305612","display_name":null,"funder_award_id":"614331","funder_id":"https://openalex.org/F4320338352","funder_display_name":"FP7 Ideas: European Research Council"}],"funders":[{"id":"https://openalex.org/F4320310490","display_name":"Villum Fonden","ror":"https://ror.org/007ww2d15"},{"id":"https://openalex.org/F4320315254","display_name":"Innovative Research Group Project of the National Natural Science Foundation of China","ror":null},{"id":"https://openalex.org/F4320338352","display_name":"FP7 Ideas: European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W204268067","https://openalex.org/W1430582609","https://openalex.org/W1502916507","https://openalex.org/W1549089649","https://openalex.org/W1800174300","https://openalex.org/W1984079283","https://openalex.org/W1989664320","https://openalex.org/W1992402998","https://openalex.org/W1997633753","https://openalex.org/W2018378172","https://openalex.org/W2027697499","https://openalex.org/W2038142281","https://openalex.org/W2062539466","https://openalex.org/W2062618908","https://openalex.org/W2075968486","https://openalex.org/W2080844740","https://openalex.org/W2086504823","https://openalex.org/W2088101210","https://openalex.org/W2089407614","https://openalex.org/W2104128006","https://openalex.org/W2107427524","https://openalex.org/W2111410263","https://openalex.org/W2114598336","https://openalex.org/W2134146845","https://openalex.org/W2152916002","https://openalex.org/W2158194525","https://openalex.org/W2163255197","https://openalex.org/W2167184472","https://openalex.org/W2397770138","https://openalex.org/W2468923260","https://openalex.org/W2508919161","https://openalex.org/W2811318564","https://openalex.org/W2938070826","https://openalex.org/W2963964051","https://openalex.org/W2964343357","https://openalex.org/W3023640601","https://openalex.org/W3098556943","https://openalex.org/W3099570205","https://openalex.org/W4235253945","https://openalex.org/W4236965008"],"related_works":["https://openalex.org/W2168583610","https://openalex.org/W2106912783","https://openalex.org/W4319992527","https://openalex.org/W2895933466","https://openalex.org/W4281867900","https://openalex.org/W2242351545","https://openalex.org/W2036753599","https://openalex.org/W2772529866","https://openalex.org/W1993530675","https://openalex.org/W2089632823"],"abstract_inverted_index":{"We":[0],"consider":[1],"static,":[2],"external":[3],"memory":[4],"indexes":[5],"for":[6,31,71],"exact":[7],"and":[8,17,143],"approximate":[9],"versions":[10],"of":[11,40,96,108,195,200,242],"the":[12,54,57,93,106,124,196,221],"k-nearest":[13],"neighbor":[14],"(k-NN)":[15],"problem,":[16],"show":[18,165,209],"new":[19,172,234],"lower":[20,58,167,210,222],"bounds":[21,168,211,223],"under":[22],"a":[23,51,150,192,233],"standard":[24],"indivisibility":[25],"assumption:":[26],"Polynomial":[27],"space":[28,36,101,142,152],"indexing":[29,90],"schemes":[30],"high-dimensional":[32],"k-NN":[33,139],"in":[34,92,140,161,183,214],"Hamming":[35,141],"cannot":[37],"take":[38],"advantage":[39],"block":[41,44,125],"transfers:":[42],"\u00ed(k)":[43],"reads":[45],"are":[46,136],"needed":[47],"to":[48,49,68,78,175,188,208,225],"answer":[50],"query.":[52],"For":[53,84,127,138],"l\u221e":[55],"metric":[56,86],"bound":[59],"holds":[60],"even":[61],"if":[62],"we":[63,169,190,231],"allow":[64],"c-appoximate":[65],"nearest":[66,115,159],"neighbors":[67,116,160],"be":[69,241],"returned,":[70],"c":[72,79],"\u2208":[73],"(1,":[74],"3).":[75],"The":[76],"restriction":[77],"<":[80],"3":[81],"is":[82,105,123],"necessary:":[83],"every":[85,144],"there":[87,148],"exists":[88,149],"an":[89],"scheme":[91],"indexability":[94],"model":[95],"Hellerstein":[97,201],"et":[98,202],"al.":[99,203],"using":[100,117],"O(kn),":[102],"where":[103,121],"n":[104,217],"number":[107],"points,":[109],"that":[110,155,177,212,239],"can":[111],"retrieve":[112],"k":[113,157],"3-approximate":[114],"optimal":[118],"\u2308k/B\u2309":[119,162],"I/Os,":[120],"B":[122],"size.":[126],"specific":[128],"metrics,":[129],"data":[130,153],"structures":[131],"with":[132],"better":[133],"approximation":[134,145,178],"factors":[135],"possible.":[137],"factor":[146],"c>1":[147],"polynomial":[151],"structure":[154],"returns":[156],"c-approximate":[158],"I/Os.":[163],"To":[164,219],"these":[166],"develop":[170,191,232],"two":[171],"techniques:":[173],"First,":[174],"handle":[176],"algorithms":[179],"have":[180],"more":[181],"freedom":[182],"deciding":[184],"which":[185],"result":[186],"set":[187],"return":[189],"relaxed":[193],"version":[194],"\u03bb-set":[197],"workload":[198],"technique":[199,205,238],"This":[204],"allows":[206],"us":[207],"hold":[213],"d":[215,226],"\u2265":[216],"dimensions.":[218],"extend":[220],"down":[224],"=":[227],"O(k":[228],"log(n/k))":[229],"dimensions,":[230],"deterministic":[235],"dimension":[236],"reduction":[237],"may":[240],"independent":[243],"interest.":[244]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}