{"id":"https://openalex.org/W2949436541","doi":"https://doi.org/10.1145/3292500.3330929","title":"Scalable Hierarchical Clustering with Tree Grafting","display_name":"Scalable Hierarchical Clustering with Tree Grafting","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2949436541","doi":"https://doi.org/10.1145/3292500.3330929","mag":"2949436541"},"language":"en","primary_location":{"id":"doi:10.1145/3292500.3330929","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330929","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330929","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330929","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Nicholas Monath","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nicholas Monath","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ari Kobren","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ari Kobren","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Akshay Krishnamurthy","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726785","display_name":"Microsoft Research New York City (United States)","ror":"https://ror.org/056zprp28","country_code":null,"type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4401726785"]},{"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":false,"raw_author_name":"Akshay Krishnamurthy","raw_affiliation_strings":["Microsoft Research, New York City, NY, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, New York City, NY, USA","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4401726785"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Michael R. Glass","orcid":null},"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":"Michael R. Glass","raw_affiliation_strings":["IBM, New York City, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM, New York City, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":null,"display_name":"Andrew McCallum","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew McCallum","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":1.5897,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.87670866,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1438","last_page":"1448"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9993000030517578,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9993000030517578,"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/T11106","display_name":"Data Management and Algorithms","score":0.9884999990463257,"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/T10057","display_name":"Face and Expression Recognition","score":0.9793000221252441,"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/cluster-analysis","display_name":"Cluster analysis","score":0.6794999837875366},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.6592000126838684},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5928999781608582},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.5490000247955322},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5461999773979187},{"id":"https://openalex.org/keywords/linkage","display_name":"Linkage (software)","score":0.5414999723434448},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5227000117301941},{"id":"https://openalex.org/keywords/complete-linkage-clustering","display_name":"Complete-linkage clustering","score":0.5095000267028809},{"id":"https://openalex.org/keywords/hierarchical-clustering-of-networks","display_name":"Hierarchical clustering of networks","score":0.4659000039100647},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4498000144958496}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6794999837875366},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6622999906539917},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.6592000126838684},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5928999781608582},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5625},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5490000247955322},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5461999773979187},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.5414999723434448},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5227000117301941},{"id":"https://openalex.org/C23822008","wikidata":"https://www.wikidata.org/wiki/Q5156437","display_name":"Complete-linkage clustering","level":5,"score":0.5095000267028809},{"id":"https://openalex.org/C82261393","wikidata":"https://www.wikidata.org/wiki/Q17038699","display_name":"Hierarchical clustering of networks","level":5,"score":0.4659000039100647},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4498000144958496},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.4458000063896179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38359999656677246},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C38734473","wikidata":"https://www.wikidata.org/wiki/Q5156506","display_name":"Complete linkage","level":5,"score":0.3781000077724457},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.36660000681877136},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3619999885559082},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C84927040","wikidata":"https://www.wikidata.org/wiki/Q6057306","display_name":"Interval tree","level":4,"score":0.349700003862381},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.3183000087738037},{"id":"https://openalex.org/C163736687","wikidata":"https://www.wikidata.org/wiki/Q17014592","display_name":"Fractal tree index","level":5,"score":0.31049999594688416},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C96147967","wikidata":"https://www.wikidata.org/wiki/Q190686","display_name":"Subroutine","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29260000586509705},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.29109999537467957},{"id":"https://openalex.org/C124527596","wikidata":"https://www.wikidata.org/wiki/Q17029359","display_name":"Hierarchical control system","level":3,"score":0.28690001368522644},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27639999985694885}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3292500.3330929","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330929","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330929","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.00076","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.00076","pdf_url":"https://arxiv.org/pdf/2001.00076","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"}],"best_oa_location":{"id":"doi:10.1145/3292500.3330929","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330929","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330929","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2158607031","display_name":null,"funder_award_id":"1763618","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307762","display_name":"International Business Machines Corporation","ror":"https://ror.org/05hh8d621"},{"id":"https://openalex.org/F4320315474","display_name":"Chan Zuckerberg Initiative","ror":"https://ror.org/02qenvm24"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2949436541.pdf","grobid_xml":"https://content.openalex.org/works/W2949436541.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2056826404","https://openalex.org/W2086179657","https://openalex.org/W2109154902","https://openalex.org/W2112090702","https://openalex.org/W2116877738","https://openalex.org/W2117539524","https://openalex.org/W2128678576","https://openalex.org/W2128999403","https://openalex.org/W2133296809","https://openalex.org/W2145862222","https://openalex.org/W2150926065","https://openalex.org/W2162021827","https://openalex.org/W2171394996","https://openalex.org/W2606287509","https://openalex.org/W2744293559","https://openalex.org/W2962769558","https://openalex.org/W2963695529","https://openalex.org/W2963737091","https://openalex.org/W4231029117"],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"Grinch,":[2],"a":[3,54,74,82],"new":[4,40,55],"algorithm":[5],"for":[6,59],"large-scale,":[7],"non-greedy":[8],"hierarchical":[9,124],"clustering":[10,60],"with":[11,47,61,73],"general":[12],"linkage":[13,62,69,106],"functions":[14],"that":[15,34,66,109],"compute":[16],"arbitrary":[17],"similarity":[18],"between":[19],"two":[20],"point":[21],"sets.":[22],"The":[23],"key":[24],"components":[25],"of":[26,45,57,89,120],"Grinch":[27,50,77,110],"are":[28],"its":[29],"rotate":[30],"and":[31,98,104,118],"graft":[32],"subroutines":[33],"efficiently":[35],"reconfigure":[36],"the":[37,68,86],"hierarchy":[38],"as":[39],"points":[41],"arrive,":[42],"supporting":[43],"discovery":[44],"clusters":[46],"complex":[48],"structure.":[49],"is":[51,71,78,111],"motivated":[52],"by":[53],"notion":[56],"separability":[58],"functions:":[63],"we":[64],"prove":[65],"when":[67],"function":[70],"consistent":[72],"ground-truth":[75],"clustering,":[76],"guaranteed":[79],"to":[80],"produce":[81],"cluster":[83],"tree":[84],"containing":[85],"ground-truth,":[87],"independent":[88],"data":[90],"arrival":[91],"order.":[92],"Our":[93],"empirical":[94],"results":[95],"on":[96],"benchmark":[97],"author":[99],"coreference":[100],"datasets":[101],"(with":[102],"standard":[103],"learned":[105],"functions)":[107],"show":[108],"more":[112],"accurate":[113],"than":[114,123],"other":[115],"scalable":[116],"methods,":[117],"orders":[119],"magnitude":[121],"faster":[122],"agglomerative":[125],"clustering.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2019-06-27T00:00:00"}