{"id":"https://openalex.org/W1455310343","doi":"https://doi.org/10.1145/2736277.2741285","title":"Asymmetric Minwise Hashing for Indexing Binary Inner Products and Set Containment","display_name":"Asymmetric Minwise Hashing for Indexing Binary Inner Products and Set Containment","publication_year":2015,"publication_date":"2015-05-18","ids":{"openalex":"https://openalex.org/W1455310343","doi":"https://doi.org/10.1145/2736277.2741285","mag":"1455310343"},"language":"en","primary_location":{"id":"doi:10.1145/2736277.2741285","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2736277.2741285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on World Wide Web","raw_type":"proceedings-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/A5024993683","display_name":"Anshumali Shrivastava","orcid":"https://orcid.org/0000-0002-5042-2856"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anshumali Shrivastava","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100741315","display_name":"Ping Li","orcid":"https://orcid.org/0000-0002-8515-7773"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ping Li","raw_affiliation_strings":["Rutgers University, Piscataway, NJ, USA","Rutgers University , Piscataway, NJ , USA ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ, USA","institution_ids":["https://openalex.org/I102322142"]},{"raw_affiliation_string":"Rutgers University , Piscataway, NJ , USA ,","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.9269,"has_fulltext":false,"cited_by_count":82,"citation_normalized_percentile":{"value":0.97894927,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"981","last_page":"991"},"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":0.9994999766349792,"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":0.9994999766349792,"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":0.991100013256073,"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":0.9797000288963318,"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/computer-science","display_name":"Computer science","score":0.7362711429595947},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.7151639461517334},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6167212128639221},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.5522345900535583},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5355740785598755},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5348421931266785},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43286412954330444},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4278733730316162},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4261588156223297},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.4224418103694916},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36958038806915283},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3546227216720581},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.31046199798583984},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14006483554840088},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.0667206346988678}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7362711429595947},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.7151639461517334},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6167212128639221},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.5522345900535583},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5355740785598755},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5348421931266785},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43286412954330444},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4278733730316162},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4261588156223297},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.4224418103694916},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36958038806915283},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3546227216720581},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.31046199798583984},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14006483554840088},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0667206346988678},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2736277.2741285","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2736277.2741285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.695.4790","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.695.4790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.www2015.it/documents/proceedings/proceedings/p981.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W107173025","https://openalex.org/W1480714498","https://openalex.org/W1541459201","https://openalex.org/W1583707981","https://openalex.org/W1671551279","https://openalex.org/W1736726159","https://openalex.org/W1768336749","https://openalex.org/W1877138905","https://openalex.org/W1974627246","https://openalex.org/W1985123706","https://openalex.org/W1986482242","https://openalex.org/W1991800036","https://openalex.org/W2007682403","https://openalex.org/W2010454887","https://openalex.org/W2012833704","https://openalex.org/W2029852131","https://openalex.org/W2065347041","https://openalex.org/W2081193615","https://openalex.org/W2085922539","https://openalex.org/W2097776316","https://openalex.org/W2097865464","https://openalex.org/W2113853816","https://openalex.org/W2120031510","https://openalex.org/W2121516976","https://openalex.org/W2123427850","https://openalex.org/W2126326837","https://openalex.org/W2126907894","https://openalex.org/W2128056631","https://openalex.org/W2132069633","https://openalex.org/W2143996849","https://openalex.org/W2147017814","https://openalex.org/W2147717514","https://openalex.org/W2150191781","https://openalex.org/W2162006472","https://openalex.org/W2167029568","https://openalex.org/W2183705191","https://openalex.org/W2397770138","https://openalex.org/W2766922894","https://openalex.org/W2963056065","https://openalex.org/W2963436558","https://openalex.org/W2963576795","https://openalex.org/W2963703787"],"related_works":["https://openalex.org/W2000601968","https://openalex.org/W2135779989","https://openalex.org/W1835589799","https://openalex.org/W2144265691","https://openalex.org/W2033383639","https://openalex.org/W2754607325","https://openalex.org/W3108918257","https://openalex.org/W144856782","https://openalex.org/W2080135560","https://openalex.org/W3016124764"],"abstract_inverted_index":{"Minwise":[0],"hashing":[1,71,134,170],"(Minhash)":[2],"is":[3,12,19,31,61,124,184],"a":[4,59,76],"widely":[5],"popular":[6],"indexing":[7],"scheme":[8,84,165],"in":[9,24,55,104,149,190],"practice.":[10,191],"Minhash":[11,43],"designed":[13],"for":[14,113,136],"estimating":[15],"set":[16,32,41,180],"resemblance":[17],"and":[18,130,186],"known":[20],"to":[21,74,78,88,188],"be":[22],"suboptimal":[23],"many":[25],"applications":[26,56],"where":[27,57],"the":[28,90,99,105,114,150,173],"desired":[29],"measure":[30],"overlap":[33],"(i.e.,":[34],"inner":[35,106,120,138],"product":[36],"between":[37],"binary":[38,119],"vectors)":[39],"or":[40],"containment.":[42,181],"has":[44],"inherent":[45],"bias":[46,91],"towards":[47,95],"smaller":[48,96],"sets,":[49,97],"which":[50],"adversely":[51],"affects":[52],"its":[53],"performance":[54],"such":[58],"penalization":[60],"not":[62],"desirable.":[63],"In":[64],"this":[65,79],"paper,":[66],"we":[67,141],"propose":[68],"asymmetric":[69,86,122],"minwise":[70],"({\\em":[72],"MH-ALSH}),":[73],"provide":[75],"solution":[77],"well-known":[80],"problem.":[81],"The":[82,163],"new":[83],"utilizes":[85],"transformations":[87],"cancel":[89],"of":[92,116,175],"traditional":[93,128],"minhash":[94,123,129],"making":[98],"final":[100],"``collision":[101],"probability''":[102],"monotonic":[103],"product.":[107],"Our":[108,182],"theoretical":[109],"comparisons":[110],"show":[111],"that,":[112],"task":[115,174],"retrieving":[117],"with":[118,179],"products,":[121],"provably":[125],"better":[126],"than":[127],"other":[131,169],"recently":[132],"proposed":[133,164],"algorithms":[135,171],"general":[137],"products.":[139],"Thus,":[140],"obtain":[142],"an":[143],"algorithmic":[144],"improvement":[145],"over":[146],"existing":[147],"approaches":[148],"literature.":[151],"Experimental":[152],"evaluations":[153],"on":[154,172],"four":[155],"publicly":[156],"available":[157],"high-dimensional":[158],"datasets":[159],"validate":[160],"our":[161],"claims.":[162],"outperforms,":[166],"often":[167],"significantly,":[168],"near":[176],"neighbor":[177],"retrieval":[178],"proposal":[183],"simple":[185],"easy":[187],"implement":[189]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}