{"id":"https://openalex.org/W2019044299","doi":"https://doi.org/10.1109/tkde.2015.2411281","title":"Efficient Similarity Join Based on Earth Mover\u2019s Distance Using MapReduce","display_name":"Efficient Similarity Join Based on Earth Mover\u2019s Distance Using MapReduce","publication_year":2015,"publication_date":"2015-03-09","ids":{"openalex":"https://openalex.org/W2019044299","doi":"https://doi.org/10.1109/tkde.2015.2411281","mag":"2019044299"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2015.2411281","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2015.2411281","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Knowledge and Data Engineering","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/A5042055991","display_name":"Jia Xu","orcid":"https://orcid.org/0000-0003-4061-8262"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]},{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Xu","raw_affiliation_strings":["Guangxi University, China","Northeastern University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi University, China","institution_ids":["https://openalex.org/I150807315"]},{"raw_affiliation_string":"Northeastern University, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056766372","display_name":"Bin Lei","orcid":"https://orcid.org/0000-0001-7625-9236"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Lei","raw_affiliation_strings":["Northeastern University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013145169","display_name":"Yu Gu","orcid":"https://orcid.org/0000-0001-7422-6254"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Gu","raw_affiliation_strings":["Northeastern University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011314280","display_name":"Marianne Winslett","orcid":"https://orcid.org/0000-0002-3935-7168"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marianne Winslett","raw_affiliation_strings":["ADSC, Illinois at Singapore Pvt. Ltd., Singapore","University of Illinois at Urbana-Champaign, Champaign, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ADSC, Illinois at Singapore Pvt. Ltd., Singapore","institution_ids":[]},{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072406974","display_name":"Ge Yu","orcid":"https://orcid.org/0000-0002-3171-8889"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge Yu","raw_affiliation_strings":["Northeastern University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100633297","display_name":"Zhenjie Zhang","orcid":"https://orcid.org/0009-0000-9080-7489"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenjie Zhang","raw_affiliation_strings":["ADSC, Illinois at Singapore Pvt. Ltd., Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ADSC, Illinois at Singapore Pvt. Ltd., Singapore","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":1.4894,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.84550074,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"27","issue":"8","first_page":"2148","last_page":"2162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9980999827384949,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9959999918937683,"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":0.858168363571167},{"id":"https://openalex.org/keywords/earth-movers-distance","display_name":"Earth mover's distance","score":0.8577059507369995},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6636368036270142},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.592418372631073},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.551814079284668},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4642767310142517},{"id":"https://openalex.org/keywords/similarity-measure","display_name":"Similarity measure","score":0.4502793550491333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4190302789211273},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.21582409739494324},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1684316098690033}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.858168363571167},{"id":"https://openalex.org/C82668687","wikidata":"https://www.wikidata.org/wiki/Q3046456","display_name":"Earth mover's distance","level":2,"score":0.8577059507369995},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6636368036270142},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.592418372631073},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.551814079284668},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4642767310142517},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.4502793550491333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4190302789211273},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.21582409739494324},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1684316098690033},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tkde.2015.2411281","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2015.2411281","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.706.1450","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.706.1450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://faculty.neu.edu.cn/ise/xujia/home/xujia-TKDE15.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2445943035","display_name":null,"funder_award_id":"61402494","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4809262640","display_name":null,"funder_award_id":"61402513","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6521477303","display_name":null,"funder_award_id":"61472071","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7989375697","display_name":null,"funder_award_id":"2012CB316201","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W596485744","https://openalex.org/W1561514023","https://openalex.org/W1983176418","https://openalex.org/W1991516927","https://openalex.org/W1991909257","https://openalex.org/W2045921448","https://openalex.org/W2049003051","https://openalex.org/W2052581258","https://openalex.org/W2053913299","https://openalex.org/W2055239866","https://openalex.org/W2065259291","https://openalex.org/W2082737904","https://openalex.org/W2097184821","https://openalex.org/W2101319014","https://openalex.org/W2104599107","https://openalex.org/W2115986770","https://openalex.org/W2116440837","https://openalex.org/W2121516976","https://openalex.org/W2143668817","https://openalex.org/W2151930506","https://openalex.org/W2154879298","https://openalex.org/W2173213060","https://openalex.org/W4256561748","https://openalex.org/W4285719527","https://openalex.org/W6617955183","https://openalex.org/W6633607392"],"related_works":["https://openalex.org/W2319693127","https://openalex.org/W2474567666","https://openalex.org/W2072263576","https://openalex.org/W2790658443","https://openalex.org/W1940044583","https://openalex.org/W2094963775","https://openalex.org/W2056226831","https://openalex.org/W2806903871","https://openalex.org/W4320802053","https://openalex.org/W3179795469"],"abstract_inverted_index":{"Earth":[0],"Mover's":[1],"Distance":[2],"(EMD)":[3],"evaluates":[4],"the":[5,55,62,77,90,97,126,141,155,175,188,193],"similarity":[6,19,23,26,66],"between":[7],"probability":[8,31],"distributions,":[9],"known":[10],"as":[11,44],"a":[12,36,103,164,183],"robust":[13],"measure":[14],"more":[15],"consistent":[16],"with":[17,33,163,182],"human":[18],"perception":[20],"than":[21,174],"traditional":[22],"functions.":[24],"EMD-based":[25],"join":[27],"retrieves":[28],"pairs":[29],"of":[30,57,64,94,121,157,167,172],"distributions":[32,118],"EMD":[34,65,122,150],"below":[35],"specified":[37],"threshold,":[38],"supporting":[39],"many":[40],"important":[41],"applications,":[42],"such":[43,80],"duplicate":[45],"image":[46,190],"retrieval":[47],"and":[48,146,178],"sensor":[49],"pattern":[50],"recognition.":[51],"This":[52],"paper":[53],"studies":[54],"possibility":[56],"using":[58,114],"MapReduce":[59,70],"to":[60,75,85,89,109,125,139],"improve":[61],"scalability":[63],"join.":[67],"While":[68],"existing":[69],"optimization":[71,134],"techniques":[72],"mainly":[73],"aim":[74],"minimize":[76],"communication":[78],"overhead,":[79],"methods":[81],"are":[82,123,136],"not":[83],"applicable":[84],"our":[86,158],"problem,":[87],"due":[88],"high":[91],"computational":[92],"cost":[93],"EMD.":[95],"Utilizing":[96],"dual-program":[98],"mapping":[99],"technique,":[100],"we":[101],"present":[102],"new":[104],"general":[105],"data":[106],"partition":[107],"framework":[108],"facilitate":[110],"effective":[111],"workload":[112],"decomposition":[113],"MapReduce,":[115],"ensuring":[116],"similar":[117],"in":[119,199],"terms":[120],"mapped":[124],"same":[127],"reduce":[128,144],"task":[129],"for":[130],"further":[131],"verification.":[132],"New":[133],"strategies":[135],"also":[137],"proposed":[138],"balance":[140],"workloads":[142],"among":[143],"tasks":[145],"eliminate":[147],"large":[148],"unnecessary":[149],"evaluations.":[151],"Our":[152],"experiments":[153],"verify":[154],"superiority":[156],"proposal":[159],"on":[160,179,192],"system":[161,180],"efficiency,":[162],"huge":[165],"advantage":[166],"at":[168],"least":[169],"one":[170],"order":[171],"magnitude":[173],"state-of-the-art":[176],"solution,":[177],"effectiveness,":[181],"real":[184],"case":[185],"study":[186],"towards":[187],"abused":[189],"phenomenon":[191],"most":[194],"popular":[195],"C2C":[196],"Web":[197],"site":[198],"China.":[200]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}