{"id":"https://openalex.org/W2604101616","doi":"https://doi.org/10.48550/arxiv.1703.04664","title":"Optimal Densification for Fast and Accurate Minwise Hashing","display_name":"Optimal Densification for Fast and Accurate Minwise Hashing","publication_year":2017,"publication_date":"2017-03-14","ids":{"openalex":"https://openalex.org/W2604101616","doi":"https://doi.org/10.48550/arxiv.1703.04664","mag":"2604101616"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1703.04664","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.04664","pdf_url":"https://arxiv.org/pdf/1703.04664","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1703.04664","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024993683","display_name":"Anshumali Shrivastava","orcid":"https://orcid.org/0000-0002-5042-2856","observed_orcids":["https://orcid.org/0000-0002-5042-2856"]},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shrivastava, Anshumali","raw_affiliation_strings":["Rice University, Houston TX#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rice University, Houston TX#TAB#","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5024993683"],"corresponding_institution_ids":["https://openalex.org/I74775410"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.7949000000953674,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.7949000000953674,"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":0.08139999955892563,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.012400000356137753,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/densification","display_name":"densification","score":0.9010000228881836},{"id":"https://openalex.org/keywords/sparse-vectors","display_name":"sparse vectors","score":0.6899999976158142},{"id":"https://openalex.org/keywords/collision-probability","display_name":"collision probability","score":0.7710000276565552},{"id":"https://openalex.org/keywords/approximate-nearest-neighbor-search","display_name":"approximate nearest neighbor search","score":0.6930000185966492},{"id":"https://openalex.org/keywords/indexing-algorithms","display_name":"indexing algorithms","score":0.453000009059906},{"id":"https://openalex.org/keywords/query-complexity","display_name":"query complexity","score":0.6190000176429749},{"id":"https://openalex.org/keywords/high-dimensional-data","display_name":"high-dimensional data","score":0.8659999966621399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7467786073684692},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.7337755560874939},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6126992106437683},{"id":"https://openalex.org/C122907437","wikidata":"https://www.wikidata.org/wiki/Q5318999","display_name":"Dynamic perfect hashing","level":5,"score":0.5748292803764343},{"id":"https://openalex.org/C116058348","wikidata":"https://www.wikidata.org/wiki/Q846912","display_name":"Universal hashing","level":5,"score":0.55441814661026},{"id":"https://openalex.org/C36375716","wikidata":"https://www.wikidata.org/wiki/Q6553456","display_name":"Linear hashing","level":5,"score":0.5185259580612183},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5057404041290283},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.4983246326446533},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4951845705509186},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4694007933139801},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4506528377532959},{"id":"https://openalex.org/C187062812","wikidata":"https://www.wikidata.org/wiki/Q6322840","display_name":"K-independent hashing","level":5,"score":0.4262728691101074},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4240821301937103},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.424032986164093},{"id":"https://openalex.org/C56856351","wikidata":"https://www.wikidata.org/wiki/Q1757218","display_name":"Consistent hashing","level":5,"score":0.4223184883594513},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4089981019496918},{"id":"https://openalex.org/C138111711","wikidata":"https://www.wikidata.org/wiki/Q478351","display_name":"Double hashing","level":4,"score":0.1926117241382599},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1616102159023285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14166563749313354},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1703.04664","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.04664","pdf_url":"https://arxiv.org/pdf/1703.04664","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"mag:2952199612","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1703.04664.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1703.04664","doi":"https://doi.org/10.48550/arxiv.1703.04664","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1703.04664","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1703.04664","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.04664","pdf_url":"https://arxiv.org/pdf/1703.04664","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1520833380","https://openalex.org/W1978024959","https://openalex.org/W1991800036","https://openalex.org/W1999092742","https://openalex.org/W2012833704","https://openalex.org/W2029852131","https://openalex.org/W2040546864","https://openalex.org/W2070996757","https://openalex.org/W2085922539","https://openalex.org/W2102221597","https://openalex.org/W2120031510","https://openalex.org/W2132069633","https://openalex.org/W2142256417","https://openalex.org/W2143996849","https://openalex.org/W2147017814","https://openalex.org/W2147717514","https://openalex.org/W2169557227","https://openalex.org/W2169660454","https://openalex.org/W2539492126","https://openalex.org/W2555576367","https://openalex.org/W2560310599","https://openalex.org/W2950150251","https://openalex.org/W2963436558","https://openalex.org/W6903433622"],"related_works":["https://openalex.org/W4385382899","https://openalex.org/W2084899141","https://openalex.org/W2076162755","https://openalex.org/W2334522381","https://openalex.org/W1486630602","https://openalex.org/W4386271002","https://openalex.org/W2811247857","https://openalex.org/W2585520041","https://openalex.org/W2094127768","https://openalex.org/W1967593546"],"abstract_inverted_index":{"Minwise":[0],"hashing":[1,11,149,185],"is":[2,28,82,100,124,133],"a":[3,36,47,107,142,146],"fundamental":[4],"and":[5,126,156,167],"one":[6],"of":[7,22,35,66,77],"the":[8,14,20,51,63,75,78,98,121,129,153,177],"most":[9],"successful":[10],"algorithm":[12],"in":[13,41,62,187],"literature.":[15],"Recent":[16],"advances":[17,55],"based":[18,70],"on":[19,71,113,164],"idea":[21],"densification~\\cite{Proc:OneHashLSH_ICML14,Proc:Shrivastava_UAI14}":[23],"have":[24,56],"shown":[25],"that":[26,120,175],"it":[27,132],"possible":[29],"to":[30,58,87,92],"compute":[31],"$k$":[32],"minwise":[33,72,94,160,184],"hashes,":[34],"vector":[37],"with":[38],"$d$":[39],"nonzeros,":[40],"mere":[42],"$(d":[43],"+":[44],"k)$":[45],"computations,":[46],"significant":[48,178],"improvement":[49,61],"over":[50],"classical":[52],"$O(dk)$.":[53],"These":[54],"led":[57],"an":[59],"algorithmic":[60],"query":[64],"complexity":[65],"traditional":[67],"indexing":[68],"algorithms":[69],"hashing.":[73,161],"Unfortunately,":[74],"variance":[76,155],"current":[79],"densification":[80,109,139],"techniques":[81],"unnecessarily":[83],"high,":[84],"which":[85,111,151],"leads":[86],"significantly":[88,134,147],"poor":[89],"accuracy":[90],"compared":[91],"vanilla":[93],"hashing,":[95],"especially":[96],"when":[97],"data":[99],"sparse.":[101],"In":[102],"this":[103],"paper,":[104],"we":[105,144],"provide":[106],"novel":[108],"scheme":[110,123,150],"relies":[112],"carefully":[114],"tailored":[115],"2-universal":[116],"hashes.":[117],"We":[118,173],"show":[119],"proposed":[122],"variance-optimal,":[125],"without":[127],"losing":[128],"runtime":[130],"efficiency,":[131],"more":[135],"accurate":[136],"than":[137],"existing":[138],"techniques.":[140],"As":[141],"result,":[143],"obtain":[145],"efficient":[148],"has":[152],"same":[154],"collision":[157],"probability":[158],"as":[159],"Experimental":[162],"evaluations":[163],"real":[165],"sparse":[166],"high-dimensional":[168],"datasets":[169],"validate":[170],"our":[171,180],"claims.":[172],"believe":[174],"given":[176],"advantages,":[179],"method":[181],"will":[182],"replace":[183],"implementations":[186],"practice.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}