{"id":"https://openalex.org/W2218762779","doi":"https://doi.org/10.1145/2902251.2902285","title":"On the Complexity of Inner Product Similarity Join","display_name":"On the Complexity of Inner Product Similarity Join","publication_year":2016,"publication_date":"2016-06-15","ids":{"openalex":"https://openalex.org/W2218762779","doi":"https://doi.org/10.1145/2902251.2902285","mag":"2218762779"},"language":"en","primary_location":{"id":"doi:10.1145/2902251.2902285","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2902251.2902285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.itu.dk/portal/da/publications/8eaf609f-8115-4a9a-a294-1163b9e8d2d5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Thomas Dybdahl Ahle","orcid":null},"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":true,"raw_author_name":"Thomas Dybdahl Ahle","raw_affiliation_strings":["IT University of Copenhagen, Copenhagen, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IT University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I83467386"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rasmus Pagh","orcid":null},"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":["IT University of Copenhagen, Copenhagen, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IT University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I83467386"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ilya Razenshteyn","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ilya Razenshteyn","raw_affiliation_strings":["MIT, Boston, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT, Boston, USA","institution_ids":["https://openalex.org/I4210110987"]}]},{"author_position":"last","author":{"id":null,"display_name":"Francesco Silvestri","orcid":null},"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":"Francesco Silvestri","raw_affiliation_strings":["IT University of Copenhagen, Copenhagen, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IT University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I83467386"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I83467386"],"apc_list":null,"apc_paid":null,"fwci":2.1963,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.91605467,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"151","last_page":"164"},"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":0.9983000159263611,"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":0.9983000159263611,"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/T11478","display_name":"Caching and Content Delivery","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9783999919891357,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.7139000296592712},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.6575000286102295},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5346999764442444},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.5223000049591064},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.5098999738693237},{"id":"https://openalex.org/keywords/exponential-function","display_name":"Exponential function","score":0.3849000036716461},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.35690000653266907},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.3553999960422516}],"concepts":[{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.7139000296592712},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.6575000286102295},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6067000031471252},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5346999764442444},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.5223000049591064},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.5098999738693237},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.45080000162124634},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.40230000019073486},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.3849000036716461},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.375900000333786},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34529998898506165},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C72782756","wikidata":"https://www.wikidata.org/wiki/Q394352","display_name":"Inner core","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.28360000252723694},{"id":"https://openalex.org/C71017364","wikidata":"https://www.wikidata.org/wiki/Q5421532","display_name":"Exponential time hypothesis","level":3,"score":0.2741999924182892},{"id":"https://openalex.org/C38976095","wikidata":"https://www.wikidata.org/wiki/Q752641","display_name":"Asymmetry","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.258899986743927}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2902251.2902285","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2902251.2902285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire/8eaf609f-8115-4a9a-a294-1163b9e8d2d5","is_oa":true,"landing_page_url":"https://pure.itu.dk/portal/da/publications/8eaf609f-8115-4a9a-a294-1163b9e8d2d5","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":"Ahle, T D, Pagh, R, Razenshteyn, I & Silvestri, F 2016, On the Complexity of Inner Product Similarity Join. in PODS '16 Proceedings of the 35th ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems. Association for Computing Machinery, pp. 151-164 . https://doi.org/10.1145/2902251.2902285","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:1510.02824","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1510.02824","pdf_url":"https://arxiv.org/pdf/1510.02824","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:www.research.unipd.it:11577/3228401","is_oa":true,"landing_page_url":"https://hdl.handle.net/11577/3228401","pdf_url":null,"source":{"id":"https://openalex.org/S4306402547","display_name":"Padua Research Archive (University of Padova)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138689650","host_organization_name":"University of Padua","host_organization_lineage":["https://openalex.org/I138689650"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/8eaf609f-8115-4a9a-a294-1163b9e8d2d5","is_oa":true,"landing_page_url":"https://pure.itu.dk/portal/da/publications/8eaf609f-8115-4a9a-a294-1163b9e8d2d5","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":"Ahle, T D, Pagh, R, Razenshteyn, I & Silvestri, F 2016, On the Complexity of Inner Product Similarity Join. in PODS '16 Proceedings of the 35th ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems. Association for Computing Machinery, pp. 151-164 . https://doi.org/10.1145/2902251.2902285","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2670930963","display_name":null,"funder_award_id":"614331","funder_id":"https://openalex.org/F4320334678","funder_display_name":"European Research Council"}],"funders":[{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1430582609","https://openalex.org/W1455310343","https://openalex.org/W1492459858","https://openalex.org/W1575370549","https://openalex.org/W1599364940","https://openalex.org/W1882355728","https://openalex.org/W1973001156","https://openalex.org/W1974627246","https://openalex.org/W1977046819","https://openalex.org/W1978475816","https://openalex.org/W1979848457","https://openalex.org/W1985289891","https://openalex.org/W2012833704","https://openalex.org/W2017851434","https://openalex.org/W2018378172","https://openalex.org/W2031248101","https://openalex.org/W2038276547","https://openalex.org/W2044163187","https://openalex.org/W2048779798","https://openalex.org/W2054141820","https://openalex.org/W2061684784","https://openalex.org/W2084732238","https://openalex.org/W2096598900","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2097796125","https://openalex.org/W2098900423","https://openalex.org/W2115500858","https://openalex.org/W2118556950","https://openalex.org/W2121269638","https://openalex.org/W2121516976","https://openalex.org/W2122146326","https://openalex.org/W2123427850","https://openalex.org/W2125980212","https://openalex.org/W2128793454","https://openalex.org/W2151584222","https://openalex.org/W2156855109","https://openalex.org/W2168356304","https://openalex.org/W2168649524","https://openalex.org/W2169795703","https://openalex.org/W2190662813","https://openalex.org/W2263882035","https://openalex.org/W2268968630","https://openalex.org/W2397770138","https://openalex.org/W2401929940","https://openalex.org/W2604829000","https://openalex.org/W2962922559","https://openalex.org/W2963593740","https://openalex.org/W3112410551","https://openalex.org/W3141299647","https://openalex.org/W6677671969","https://openalex.org/W6739971681","https://openalex.org/W7000791799"],"related_works":[],"abstract_inverted_index":{"A":[0,163],"number":[1],"of":[2,18,27,51,103,120,160],"tasks":[3],"in":[4,29,123],"classification,":[5],"information":[6],"retrieval,":[7],"recommendation":[8],"systems,":[9],"and":[10,48,80,111,134],"record":[11],"linkage":[12],"reduce":[13],"to":[14,154],"the":[15,57,91,127,151,157],"core":[16],"problem":[17],"inner":[19,37,52,104],"product":[20,105],"similarity":[21,106],"join":[22,40,122],"(IPS":[23],"join):":[24],"identifying":[25],"pairs":[26],"vectors":[28,45,61],"a":[30,34,100],"collection":[31],"that":[32,144,174],"have":[33,63,83],"sufficiently":[35],"large":[36],"product.":[38],"IPS":[39,121,168],"is":[41,54],"well":[42],"understood":[43],"when":[44],"are":[46,178],"normalized":[47],"some":[49],"approximation":[50],"products":[53],"allowed.":[55],"However,":[56],"general":[58],"case":[59],"where":[60],"may":[62],"any":[64],"length":[65],"appears":[66],"much":[67],"more":[68],"challenging.":[69],"Recently,":[70],"new":[71,109,164],"upper":[72,112,133],"bounds":[73,136],"based":[74,169],"on":[75,90,170],"asymmetric":[76,81],"locality-sensitive":[77],"hashing":[78],"(ALSH)":[79],"embeddings":[82],"emerged,":[84],"but":[85],"little":[86],"has":[87],"been":[88],"known":[89],"lower":[92,110,135],"bound":[93],"side.":[94],"In":[95,140],"this":[96],"paper":[97],"we":[98,142],"initiate":[99],"systematic":[101],"study":[102],"join,":[107],"showing":[108],"bounds.":[113],"Our":[114],"main":[115],"results":[116,177],"are:":[117],"Approximation":[118],"hardness":[119,176],"subquadratic":[124],"time,":[125],"assuming":[126],"strong":[128],"exponential":[129],"time":[130],"hypothesis.":[131],"New":[132],"for":[137,167],"(A)LSH-based":[138],"algorithms.":[139],"particular,":[141],"show":[143],"asymmetry":[145],"can":[146],"be":[147],"avoided":[148],"by":[149],"relaxing":[150],"LSH":[152],"definition":[153],"only":[155],"consider":[156],"collision":[158],"probability":[159],"distinct":[161],"elements.":[162],"indexing":[165],"method":[166],"linear":[171],"sketches,":[172],"implying":[173],"our":[175],"not":[179],"far":[180],"from":[181],"being":[182],"tight.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2}],"updated_date":"2026-05-19T08:33:51.333923","created_date":"2016-06-24T00:00:00"}