{"id":"https://openalex.org/W2076177156","doi":"https://doi.org/10.1145/2505515.2505527","title":"Efficient hierarchical clustering of large high dimensional datasets","display_name":"Efficient hierarchical clustering of large high dimensional datasets","publication_year":2013,"publication_date":"2013-10-27","ids":{"openalex":"https://openalex.org/W2076177156","doi":"https://doi.org/10.1145/2505515.2505527","mag":"2076177156"},"language":"en","primary_location":{"id":"doi:10.1145/2505515.2505527","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2505515.2505527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5034610400","display_name":"Sean Gilpin","orcid":"https://orcid.org/0000-0002-8973-8575"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sean Gilpin","raw_affiliation_strings":["University of California, Davis, Davis, CA, USA","University of California Davis  Davis CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Davis, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"University of California Davis  Davis CA USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074506574","display_name":"Buyue Qian","orcid":"https://orcid.org/0000-0003-4780-5677"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Buyue Qian","raw_affiliation_strings":["IBM, Yorktown Heights, NY, USA","IBM, Yorktown Heights, NY USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM, Yorktown Heights, NY, USA","institution_ids":[]},{"raw_affiliation_string":"IBM, Yorktown Heights, NY USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030289182","display_name":"Ian Davidson","orcid":"https://orcid.org/0000-0002-1258-4213"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Davidson","raw_affiliation_strings":["University of California, Davis, Davis, CA, USA","University of California Davis  Davis CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Davis, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"University of California Davis  Davis CA USA","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6236,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.7002176,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1371","last_page":"1380"},"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":0.9997000098228455,"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":0.9997000098228455,"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/T11106","display_name":"Data Management and Algorithms","score":0.9916999936103821,"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"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9850000143051147,"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/computer-science","display_name":"Computer science","score":0.7738268375396729},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.7611832618713379},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.619493305683136},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.6152215003967285},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5830798149108887},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.5705552101135254},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4814559817314148},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.47766122221946716},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.44293391704559326},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4203813970088959},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34104567766189575},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32301628589630127},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13556328415870667},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13188236951828003}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7738268375396729},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.7611832618713379},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.619493305683136},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.6152215003967285},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5830798149108887},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.5705552101135254},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4814559817314148},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.47766122221946716},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.44293391704559326},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4203813970088959},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34104567766189575},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32301628589630127},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13556328415870667},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13188236951828003},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2505515.2505527","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2505515.2505527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W8870360","https://openalex.org/W143174683","https://openalex.org/W1493526108","https://openalex.org/W1516407653","https://openalex.org/W2036216970","https://openalex.org/W2049758109","https://openalex.org/W2066680326","https://openalex.org/W2105572632","https://openalex.org/W2107946060","https://openalex.org/W2120636855","https://openalex.org/W2141656507","https://openalex.org/W2145036943","https://openalex.org/W2145607950","https://openalex.org/W2152818382","https://openalex.org/W2612166593","https://openalex.org/W2913066018","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W2804364458","https://openalex.org/W4298130764","https://openalex.org/W2132641928","https://openalex.org/W2090259340","https://openalex.org/W4310225030","https://openalex.org/W1835589799","https://openalex.org/W2144265691","https://openalex.org/W1605991620","https://openalex.org/W4387251676","https://openalex.org/W4385261619"],"abstract_inverted_index":{"Hierarchical":[0],"clustering":[1],"is":[2,53,66,172,190],"extensively":[3],"used":[4,22],"to":[5,91,109,116,124,134,156],"organize":[6],"high":[7,73],"dimensional":[8],"objects":[9,65,97,111,128,149],"such":[10,64],"as":[11,46,48,192],"documents":[12],"and":[13,75,133,194],"images":[14],"into":[15],"a":[16,24,89],"structure":[17],"which":[18],"can":[19,44,195],"then":[20],"be":[21,45,197],"in":[23,33,79,82,150],"multitude":[25],"of":[26,40,56,61,88,94,127,148,176,187],"ways.":[27],"However,":[28],"existing":[29],"algorithms":[30,43,182],"are":[31,72],"limited":[32],"their":[34],"application":[35],"since":[36],"the":[37,54,59,85,117,137,146,151,185],"time":[38,68],"complexity":[39],"agglomerative":[41,159,181],"style":[42],"much":[47],"O(n2log":[49],"n)":[50],"where":[51],"n":[52],"number":[55],"objects.":[57],"Furthermore":[58],"computation":[60],"similarity":[62,147],"between":[63],"itself":[67],"consuming":[69],"given":[70],"they":[71],"dimension":[74],"even":[76],"optimized":[77],"built":[78],"functions":[80],"found":[81],"MATLAB":[83],"take":[84],"best":[86],"part":[87],"day":[90],"handle":[92],"collections":[93],"just":[95],"10,000":[96],"on":[98,145],"typical":[99],"machines.":[100],"In":[101],"this":[102,154],"paper":[103],"we":[104],"explore":[105],"using":[106],"angular":[107,114],"hashing":[108],"hash":[110,119,131,138],"with":[112,161],"similar":[113],"distance":[115],"same":[118,152],"bucket.":[120],"This":[121],"allows":[122],"us":[123],"create":[125],"hierarchies":[126],"within":[129],"each":[130],"bucket":[132,153],"hierarchically":[135],"cluster":[136],"buckets":[139],"themselves.":[140],"With":[141],"our":[142,173,188],"formal":[143],"guarantees":[144],"leads":[155],"an":[157],"elegant":[158],"algorithm":[160],"strong":[162],"performance":[163],"bounds.":[164],"Our":[165],"experimental":[166],"results":[167,189],"show":[168],"that":[169],"not":[170],"only":[171],"approach":[174],"thousands":[175],"times":[177],"faster":[178],"than":[179],"regular":[180],"but":[183],"surprisingly":[184],"accuracy":[186],"typically":[191],"good":[193],"sometimes":[196],"substantially":[198],"better.":[199]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2015,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}