{"id":"https://openalex.org/W2168713405","doi":"https://doi.org/10.1145/1376916.1376946","title":"The power of two min-hashes for similarity search among hierarchical data objects","display_name":"The power of two min-hashes for similarity search among hierarchical data objects","publication_year":2008,"publication_date":"2008-06-09","ids":{"openalex":"https://openalex.org/W2168713405","doi":"https://doi.org/10.1145/1376916.1376946","mag":"2168713405"},"language":"en","primary_location":{"id":"doi:10.1145/1376916.1376946","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1376916.1376946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the twenty-seventh ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems","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/A5039201046","display_name":"Sreenivas Gollapudi","orcid":"https://orcid.org/0000-0002-5732-3164"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sreenivas Gollapudi","raw_affiliation_strings":["Microsoft Research, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085651536","display_name":"Rina Panigrahy\u200e","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rina Panigrahy","raw_affiliation_strings":["Micsrosoft Research, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Micsrosoft Research, Mountain View, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5039201046"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":0.355,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.68589441,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"211","last_page":"220"},"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":0.9998999834060669,"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":0.9998999834060669,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9865999817848206,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9819999933242798,"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/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.8191472887992859},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.7584431767463684},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6354082822799683},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.6151257753372192},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6000112295150757},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5961445569992065},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5862110257148743},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.5739153623580933},{"id":"https://openalex.org/keywords/weight-balanced-tree","display_name":"Weight-balanced tree","score":0.5461077690124512},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5389310717582703},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.48793575167655945},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.4851280152797699},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.45595553517341614},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.45277857780456543},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.443391889333725},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.43839070200920105},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.4328484535217285},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.43213993310928345},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.38096269965171814},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34601303935050964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31397002935409546},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.2666572332382202},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2548404335975647},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2322198450565338},{"id":"https://openalex.org/keywords/binary-tree","display_name":"Binary tree","score":0.13381928205490112},{"id":"https://openalex.org/keywords/binary-search-tree","display_name":"Binary search tree","score":0.09147268533706665},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08228129148483276}],"concepts":[{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.8191472887992859},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.7584431767463684},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6354082822799683},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.6151257753372192},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6000112295150757},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5961445569992065},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5862110257148743},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5739153623580933},{"id":"https://openalex.org/C57900377","wikidata":"https://www.wikidata.org/wiki/Q7979855","display_name":"Weight-balanced tree","level":4,"score":0.5461077690124512},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5389310717582703},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.48793575167655945},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.4851280152797699},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.45595553517341614},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.45277857780456543},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.443391889333725},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.43839070200920105},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.4328484535217285},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.43213993310928345},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38096269965171814},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34601303935050964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31397002935409546},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.2666572332382202},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2548404335975647},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2322198450565338},{"id":"https://openalex.org/C197855036","wikidata":"https://www.wikidata.org/wiki/Q380172","display_name":"Binary tree","level":2,"score":0.13381928205490112},{"id":"https://openalex.org/C91154448","wikidata":"https://www.wikidata.org/wiki/Q623818","display_name":"Binary search tree","level":3,"score":0.09147268533706665},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08228129148483276},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1376916.1376946","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1376916.1376946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the twenty-seventh ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.155.4909","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.155.4909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://theory.stanford.edu/~rinap/papers/treesimpods.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.530.3683","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.530.3683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://research.microsoft.com/pubs/74004/pods2008a.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W403955","https://openalex.org/W192724328","https://openalex.org/W1502916507","https://openalex.org/W1875120328","https://openalex.org/W1976373002","https://openalex.org/W1978510388","https://openalex.org/W1996186909","https://openalex.org/W2012833704","https://openalex.org/W2024797550","https://openalex.org/W2056708848","https://openalex.org/W2061980234","https://openalex.org/W2071572981","https://openalex.org/W2081193615","https://openalex.org/W2085533860","https://openalex.org/W2122899550","https://openalex.org/W2132069633","https://openalex.org/W2147717514","https://openalex.org/W2147909264","https://openalex.org/W2148029272","https://openalex.org/W2162006472","https://openalex.org/W6773252166"],"related_works":["https://openalex.org/W2135779989","https://openalex.org/W2144265691","https://openalex.org/W2754607325","https://openalex.org/W144856782","https://openalex.org/W2080135560","https://openalex.org/W2147226516","https://openalex.org/W2975588143","https://openalex.org/W2010970209","https://openalex.org/W2752074276","https://openalex.org/W2064670891"],"abstract_inverted_index":{"In":[0],"this":[1],"study":[2],"we":[3,14,186,200],"propose":[4],"sketching":[5],"algorithms":[6],"for":[7],"comput-ing":[8],"similarities":[9],"between":[10,86],"hierarchical":[11],"data.":[12],"Specifically,":[13,185],"look":[15],"at":[16,30],"data":[17],"objects":[18],"that":[19,93,202],"are":[20,39,170,178],"represented":[21,51],"using":[22,88],"leaf-labeled":[23,114],"trees":[24,87,115,130,147,169,177,191],"denoting":[25],"a":[26,35,43,47,53,69,79],"set":[27,80,138],"of":[28,55,81,97,116,131,139,144,154,161,189],"elements":[29],"the":[31,66,75,89,95,113,152,159,175,181,197],"leaves":[32],"organized":[33],"in":[34,65,151,207,216],"hierarchy.":[36,67],"Such":[37,68],"representations":[38],"richer":[40,72],"alternatives":[41],"to":[42,106,129],"set.":[44],"For":[45],"example,":[46],"document":[48,76],"can":[49,119,125],"be":[50,120,126],"as":[52,78,122,137],"hierarchy":[54],"sets":[56,123],"wherein":[57],"chapters,":[58],"sections,":[59],"and":[60,124,148,172],"paragraphs":[61],"represent":[62],"different":[63],"levels":[64],"represen-tation":[70],"is":[71,104,165],"than":[73],"viewing":[74,135],"simply":[77],"words.":[82],"We":[83,141],"measure":[84,103,111],"distance":[85,102,183],"best":[90],"possible":[91],"super-imposition":[92],"minimizes":[94],"number":[96],"mis-matched":[98],"leaf":[99],"labels.":[100],"Our":[101],"equivalent":[105],"an":[107],"Earth":[108],"Mover\u2019s":[109],"Distance":[110],"since":[112],"height":[117,133],"one":[118,204],"viewed":[121],"recur-sively":[127],"extended":[128],"larger":[132],"by":[134,192],"them":[136,150],"sets.":[140],"compute":[142,187],"sketches":[143,163,188],"arbitrary":[145],"weighted":[146],"analyze":[149],"context":[153],"locality-sensitive":[155],"hash-ing":[156],"(LSH)":[157],"where":[158],"probability":[160],"two":[162,168,176,213],"matching":[164],"high":[166],"when":[167,174],"similar":[171],"low":[173],"far":[179],"under":[180],"given":[182],"measure.":[184],"such":[190],"propagating":[193,212],"min-hash":[194,205],"computations":[195],"up":[196],"tree.":[198],"Furthermore,":[199],"show":[201],"prop-agating":[203],"results":[206,215],"poor":[208],"sketch":[209],"properties":[210],"while":[211],"min-hashes":[214],"good":[217],"sketches.":[218]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}