{"id":"https://openalex.org/W2031913229","doi":"https://doi.org/10.1145/2020408.2020508","title":"Unsupervised clustering of multidimensional distributions using earth mover distance","display_name":"Unsupervised clustering of multidimensional distributions using earth mover distance","publication_year":2011,"publication_date":"2011-08-21","ids":{"openalex":"https://openalex.org/W2031913229","doi":"https://doi.org/10.1145/2020408.2020508","mag":"2031913229"},"language":"en","primary_location":{"id":"doi:10.1145/2020408.2020508","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2020408.2020508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining","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/A5071051767","display_name":"David Applegate","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Applegate","raw_affiliation_strings":["AT&T Labs - Research, Florham Park, NJ, USA","AT&T Labs---Research, Florham Park, NJ, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Labs - Research, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Labs---Research, Florham Park, NJ, USA#TAB#","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086114454","display_name":"Tamraparni Dasu","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tamraparni Dasu","raw_affiliation_strings":["AT&T Labs - Research, Florham Park, NJ, USA","AT&T Labs---Research, Florham Park, NJ, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Labs - Research, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Labs---Research, Florham Park, NJ, USA#TAB#","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017504840","display_name":"Shankar Krishnan","orcid":"https://orcid.org/0000-0002-0374-1352"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shankar Krishnan","raw_affiliation_strings":["AT&T Labs - Research, Florham Park, NJ, USA","AT&T Labs---Research, Florham Park, NJ, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Labs - Research, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Labs---Research, Florham Park, NJ, USA#TAB#","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029437914","display_name":"Simon Urbanek","orcid":"https://orcid.org/0000-0003-2297-1732"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simon Urbanek","raw_affiliation_strings":["AT&T Labs - Research, Florham Park, NJ, USA","AT&T Labs---Research, Florham Park, NJ, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Labs - Research, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Labs---Research, Florham Park, NJ, USA#TAB#","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":3.7769,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.9442747,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"636","last_page":"644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9965000152587891,"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":0.9965000152587891,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9952999949455261,"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/T11106","display_name":"Data Management and Algorithms","score":0.9915000200271606,"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/earth-movers-distance","display_name":"Earth mover's distance","score":0.8210039138793945},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8077934980392456},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.672012448310852},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6539207100868225},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5786258578300476},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.48933929204940796},{"id":"https://openalex.org/keywords/euclidean-space","display_name":"Euclidean space","score":0.46435096859931946},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.43692585825920105},{"id":"https://openalex.org/keywords/metric-space","display_name":"Metric space","score":0.43236225843429565},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4079242944717407},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.3235706686973572},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24932444095611572},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0882692039012909}],"concepts":[{"id":"https://openalex.org/C82668687","wikidata":"https://www.wikidata.org/wiki/Q3046456","display_name":"Earth mover's distance","level":2,"score":0.8210039138793945},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8077934980392456},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.672012448310852},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6539207100868225},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5786258578300476},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.48933929204940796},{"id":"https://openalex.org/C186450821","wikidata":"https://www.wikidata.org/wiki/Q17295","display_name":"Euclidean space","level":2,"score":0.46435096859931946},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.43692585825920105},{"id":"https://openalex.org/C198043062","wikidata":"https://www.wikidata.org/wiki/Q180953","display_name":"Metric space","level":2,"score":0.43236225843429565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4079242944717407},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.3235706686973572},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24932444095611572},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0882692039012909},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2020408.2020508","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2020408.2020508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining","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":20,"referenced_works":["https://openalex.org/W152055444","https://openalex.org/W1557310162","https://openalex.org/W1597286033","https://openalex.org/W2032916024","https://openalex.org/W2038943263","https://openalex.org/W2039682702","https://openalex.org/W2080713965","https://openalex.org/W2125101937","https://openalex.org/W2131458019","https://openalex.org/W2131940723","https://openalex.org/W2134902330","https://openalex.org/W2137243801","https://openalex.org/W2143668817","https://openalex.org/W2158787690","https://openalex.org/W2160754518","https://openalex.org/W2163380389","https://openalex.org/W2171235719","https://openalex.org/W2995395573","https://openalex.org/W3127518054","https://openalex.org/W4232041434"],"related_works":["https://openalex.org/W1543731900","https://openalex.org/W4366087900","https://openalex.org/W2027475040","https://openalex.org/W2136810907","https://openalex.org/W1642991110","https://openalex.org/W4247856301","https://openalex.org/W2115336194","https://openalex.org/W2105228010","https://openalex.org/W1605858995","https://openalex.org/W2749646986"],"abstract_inverted_index":{"Multidimensional":[0],"distributions":[1],"are":[2],"often":[3],"used":[4],"in":[5,25,53],"data":[6],"mining":[7],"to":[8,20],"describe":[9],"and":[10,57],"summarize":[11],"different":[12],"features":[13],"of":[14,38],"large":[15],"datasets.":[16],"It":[17],"is":[18],"natural":[19],"look":[21],"for":[22,61],"distinct":[23],"classes":[24],"such":[26],"datasets":[27],"by":[28],"clustering":[29],"the":[30,36,44,50,54,65],"data.":[31],"A":[32],"common":[33],"approach":[34],"entails":[35],"use":[37],"methods":[39],"like":[40],"k-means":[41,45],"clustering.":[42],"However,":[43],"method":[46],"inherently":[47],"relies":[48],"on":[49],"Euclidean":[51],"metric":[52],"embedded":[55],"space":[56],"does":[58],"not":[59],"account":[60],"additional":[62],"topology":[63],"underlying":[64],"distribution.":[66]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}