{"id":"https://openalex.org/W2399595210","doi":"https://doi.org/10.1109/tpds.2015.2462354","title":"<sc>Heads-Join:</sc> Efficient Earth Mover's Distance Similarity Joins on Hadoop","display_name":"<sc>Heads-Join:</sc> Efficient Earth Mover's Distance Similarity Joins on Hadoop","publication_year":2015,"publication_date":"2015-07-29","ids":{"openalex":"https://openalex.org/W2399595210","doi":"https://doi.org/10.1109/tpds.2015.2462354","mag":"2399595210"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2015.2462354","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2015.2462354","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5101876397","display_name":"Jin Huang","orcid":"https://orcid.org/0009-0003-7343-108X"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Jin Huang","raw_affiliation_strings":["Department of Information and Computing Systems, University of Melbourne, Melbourne, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Department of Information and Computing Systems, University of Melbourne, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100422092","display_name":"Rui Zhang","orcid":"https://orcid.org/0000-0002-8132-6250"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Rui Zhang","raw_affiliation_strings":["Department of Information and Computing Systems, University of Melbourne, Melbourne, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Department of Information and Computing Systems, University of Melbourne, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014716105","display_name":"Rajkumar Buyya","orcid":"https://orcid.org/0000-0001-9754-6496"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Rajkumar Buyya","raw_affiliation_strings":["Department of Information and Computing Systems, University of Melbourne, Melbourne, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Department of Information and Computing Systems, University of Melbourne, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100326501","display_name":"Jian Chen","orcid":"https://orcid.org/0000-0003-4769-1526"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Chen","raw_affiliation_strings":["School of Software Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115602897","display_name":"Yongwei Wu","orcid":"https://orcid.org/0000-0002-6651-7032"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongwei Wu","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua National Laboratory for Information Science and Technology (TNLIST), Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua National Laboratory for Information Science and Technology (TNLIST), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101876397"],"corresponding_institution_ids":["https://openalex.org/I165779595"],"apc_list":null,"apc_paid":null,"fwci":0.936,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.8355989,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"27","issue":"6","first_page":"1660","last_page":"1673"},"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":0.9993000030517578,"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":0.9993000030517578,"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":0.9990000128746033,"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":0.9975000023841858,"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/joins","display_name":"Joins","score":0.8462357521057129},{"id":"https://openalex.org/keywords/earth-movers-distance","display_name":"Earth mover's distance","score":0.7982004880905151},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7831960916519165},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6383400559425354},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.6344375610351562},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4886684715747833},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.445911705493927},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42336559295654297},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4030534625053406},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3769097924232483},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34253203868865967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24934014678001404},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14393272995948792},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13554629683494568}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.8462357521057129},{"id":"https://openalex.org/C82668687","wikidata":"https://www.wikidata.org/wiki/Q3046456","display_name":"Earth mover's distance","level":2,"score":0.7982004880905151},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7831960916519165},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6383400559425354},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.6344375610351562},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4886684715747833},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.445911705493927},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42336559295654297},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4030534625053406},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3769097924232483},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34253203868865967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24934014678001404},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14393272995948792},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13554629683494568},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2015.2462354","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2015.2462354","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.5400000214576721}],"awards":[{"id":"https://openalex.org/G4006564843","display_name":null,"funder_award_id":"61433008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5519571499","display_name":null,"funder_award_id":"2015ZZ029","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5978375883","display_name":null,"funder_award_id":"U1435216","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6363502972","display_name":null,"funder_award_id":"FT120100832","funder_id":"https://openalex.org/F4320338275","funder_display_name":"Division of Arctic Sciences"},{"id":"https://openalex.org/G6417942114","display_name":null,"funder_award_id":"FT120100545","funder_id":"https://openalex.org/F4320338275","funder_display_name":"Division of Arctic Sciences"},{"id":"https://openalex.org/G7260597857","display_name":null,"funder_award_id":"61170210","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8330345586","display_name":null,"funder_award_id":"DP130104587","funder_id":"https://openalex.org/F4320338275","funder_display_name":"Division of Arctic Sciences"},{"id":"https://openalex.org/G8973672947","display_name":null,"funder_award_id":"61373145","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320338275","display_name":"Division of Arctic Sciences","ror":"https://ror.org/02trddg58"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1448681276","https://openalex.org/W1556219185","https://openalex.org/W1608675337","https://openalex.org/W1976821017","https://openalex.org/W1977338887","https://openalex.org/W1983176418","https://openalex.org/W1991909257","https://openalex.org/W2031913229","https://openalex.org/W2043099794","https://openalex.org/W2045271686","https://openalex.org/W2045921448","https://openalex.org/W2049003051","https://openalex.org/W2051468257","https://openalex.org/W2055239866","https://openalex.org/W2061601738","https://openalex.org/W2062734663","https://openalex.org/W2074474336","https://openalex.org/W2093050254","https://openalex.org/W2101319014","https://openalex.org/W2104599107","https://openalex.org/W2107711468","https://openalex.org/W2115500858","https://openalex.org/W2116790095","https://openalex.org/W2143668817","https://openalex.org/W2144967509","https://openalex.org/W2151930506","https://openalex.org/W2170942078","https://openalex.org/W2173213060","https://openalex.org/W4256561748"],"related_works":["https://openalex.org/W2393491644","https://openalex.org/W4206577045","https://openalex.org/W650102067","https://openalex.org/W3086237447","https://openalex.org/W2740404111","https://openalex.org/W1550806730","https://openalex.org/W1496672428","https://openalex.org/W2589740103","https://openalex.org/W1966967794","https://openalex.org/W2397450670"],"abstract_inverted_index":{"The":[0,158],"Earth":[1],"Mover's":[2],"Distance":[3],"(EMD)":[4],"similarity":[5,37,66,167],"join":[6,38,67,168],"has":[7,119],"a":[8,89,110],"number":[9],"of":[10,28,44,100,177],"important":[11],"applications":[12],"such":[13],"as":[14],"near":[15],"duplicate":[16],"image":[17],"retrieval":[18],"and":[19,33,80,104,107,128,131,146,155,179],"distributed":[20],"based":[21],"pattern":[22],"analysis.":[23],"However,":[24],"the":[25,35,52,58,62,98,164],"computational":[26],"cost":[27,112],"EMD":[29,36,101,116],"is":[30,40],"super":[31],"cubic":[32],"consequently":[34],"operation":[39],"prohibitive":[41],"for":[42],"datasets":[43],"even":[45],"medium":[46],"size.":[47],"We":[48,87,124,148],"propose":[49,88],"to":[50,55,69,83,174],"employ":[51],"Hadoop":[53,70,138],"platform":[54],"speed":[56],"up":[57,173],"operation.":[59],"Simply":[60],"porting":[61],"state-of-the-art":[63,165],"metric":[64,166],"distance":[65,78],"algorithms":[68,134],"results":[71,159],"in":[72],"inefficiency":[73],"because":[74,113],"they":[75],"involve":[76],"excessive":[77],"computations":[79],"are":[81],"vulnerable":[82],"skewed":[84],"data":[85,96],"distributions.":[86],"novel":[90],"framework,":[91],"named":[92],"HEADS-JOIN,":[93],"which":[94],"transforms":[95],"into":[97],"space":[99],"lower":[102,117],"bounds":[103,118],"performs":[105],"pruning":[106],"partitioning":[108],"at":[109],"low":[111],"computing":[114],"these":[115],"constant":[120],"or":[121],"linear":[122],"complexity.":[123],"investigate":[125],"both":[126,153],"range":[127],"top-k":[129],"joins,":[130],"design":[132],"efficient":[133],"on":[135,152],"three":[136],"popular":[137],"computation":[139],"paradigms,":[140],"i.e.,":[141,170],"MapReduce,":[142],"Bulk":[143],"Synchronous":[144],"Parallel,":[145],"Spark.":[147],"conduct":[149],"extensive":[150],"experiments":[151],"real":[154],"synthetic":[156],"datasets.":[157],"show":[160],"that":[161],"HEADS-JOIN":[162],"outperforms":[163],"technique,":[169],"Quickjoin,":[171],"by":[172],"an":[175],"order":[176],"magnitude":[178],"scales":[180],"out":[181],"well.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}