{"id":"https://openalex.org/W4398250068","doi":"https://doi.org/10.1007/s10766-024-00772-1","title":"LSH SimilarityJoin Pattern in FastFlow","display_name":"LSH SimilarityJoin Pattern in FastFlow","publication_year":2024,"publication_date":"2024-05-23","ids":{"openalex":"https://openalex.org/W4398250068","doi":"https://doi.org/10.1007/s10766-024-00772-1"},"language":"en","primary_location":{"id":"doi:10.1007/s10766-024-00772-1","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1007/s10766-024-00772-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10766-024-00772-1.pdf","source":{"id":"https://openalex.org/S148521650","display_name":"International Journal of Parallel Programming","issn_l":"0885-7458","issn":["0885-7458","1573-7640"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Parallel Programming","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10766-024-00772-1.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071107206","display_name":"Nicol\u00f2 Tonci","orcid":"https://orcid.org/0009-0003-3631-0756"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Nicol\u00f2 Tonci","raw_affiliation_strings":["Computer Science Department, University of Pisa, Pisa, Italy","University of Pisa - Universit\u00e0 di Pisa (Lungarno Pacinotti 43 - 56126 Pisa - Italy)"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Pisa, Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]},{"raw_affiliation_string":"University of Pisa - Universit\u00e0 di Pisa (Lungarno Pacinotti 43 - 56126 Pisa - Italy)","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019906829","display_name":"S\u00e9bastien Rivault","orcid":null},"institutions":[{"id":"https://openalex.org/I12449238","display_name":"Universit\u00e9 d'Orl\u00e9ans","ror":"https://ror.org/014zrew76","country_code":"FR","type":"education","lineage":["https://openalex.org/I12449238"]},{"id":"https://openalex.org/I4387153997","display_name":"Laboratoire d'Informatique Fondamentale d'Orl\u00e9ans","ror":"https://ror.org/01nr3td38","country_code":null,"type":"facility","lineage":["https://openalex.org/I12449238","https://openalex.org/I4210143826","https://openalex.org/I4387153997"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"S\u00e9bastien Rivault","raw_affiliation_strings":["Universit\u00e9 d\u2019Orl\u00e9ans, Orl\u00e9ans, France","LIFO - Laboratoire d'Informatique Fondamentale d'Orl\u00e9ans (B\u00e2timent IIIA, Rue L\u00e9onard de Vinci, B.P. 6759, F-45067 ORLEANS Cedex 2 - France)"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 d\u2019Orl\u00e9ans, Orl\u00e9ans, France","institution_ids":["https://openalex.org/I12449238"]},{"raw_affiliation_string":"LIFO - Laboratoire d'Informatique Fondamentale d'Orl\u00e9ans (B\u00e2timent IIIA, Rue L\u00e9onard de Vinci, B.P. 6759, F-45067 ORLEANS Cedex 2 - France)","institution_ids":["https://openalex.org/I4387153997"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084713903","display_name":"Mostafa Bamha","orcid":"https://orcid.org/0000-0003-1235-4167"},"institutions":[{"id":"https://openalex.org/I4387153997","display_name":"Laboratoire d'Informatique Fondamentale d'Orl\u00e9ans","ror":"https://ror.org/01nr3td38","country_code":null,"type":"facility","lineage":["https://openalex.org/I12449238","https://openalex.org/I4210143826","https://openalex.org/I4387153997"]},{"id":"https://openalex.org/I12449238","display_name":"Universit\u00e9 d'Orl\u00e9ans","ror":"https://ror.org/014zrew76","country_code":"FR","type":"education","lineage":["https://openalex.org/I12449238"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mostafa Bamha","raw_affiliation_strings":["Universit\u00e9 d\u2019Orl\u00e9ans, Orl\u00e9ans, France","LIFO - Laboratoire d'Informatique Fondamentale d'Orl\u00e9ans (B\u00e2timent IIIA, Rue L\u00e9onard de Vinci, B.P. 6759, F-45067 ORLEANS Cedex 2 - France)"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 d\u2019Orl\u00e9ans, Orl\u00e9ans, France","institution_ids":["https://openalex.org/I12449238"]},{"raw_affiliation_string":"LIFO - Laboratoire d'Informatique Fondamentale d'Orl\u00e9ans (B\u00e2timent IIIA, Rue L\u00e9onard de Vinci, B.P. 6759, F-45067 ORLEANS Cedex 2 - France)","institution_ids":["https://openalex.org/I4387153997"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082820960","display_name":"Sophie Robert","orcid":"https://orcid.org/0000-0003-4359-9124"},"institutions":[{"id":"https://openalex.org/I12449238","display_name":"Universit\u00e9 d'Orl\u00e9ans","ror":"https://ror.org/014zrew76","country_code":"FR","type":"education","lineage":["https://openalex.org/I12449238"]},{"id":"https://openalex.org/I4387153997","display_name":"Laboratoire d'Informatique Fondamentale d'Orl\u00e9ans","ror":"https://ror.org/01nr3td38","country_code":null,"type":"facility","lineage":["https://openalex.org/I12449238","https://openalex.org/I4210143826","https://openalex.org/I4387153997"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sophie Robert","raw_affiliation_strings":["Universit\u00e9 d\u2019Orl\u00e9ans, Orl\u00e9ans, France","LIFO - Laboratoire d'Informatique Fondamentale d'Orl\u00e9ans (B\u00e2timent IIIA, Rue L\u00e9onard de Vinci, B.P. 6759, F-45067 ORLEANS Cedex 2 - France)"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 d\u2019Orl\u00e9ans, Orl\u00e9ans, France","institution_ids":["https://openalex.org/I12449238"]},{"raw_affiliation_string":"LIFO - Laboratoire d'Informatique Fondamentale d'Orl\u00e9ans (B\u00e2timent IIIA, Rue L\u00e9onard de Vinci, B.P. 6759, F-45067 ORLEANS Cedex 2 - France)","institution_ids":["https://openalex.org/I4387153997"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050247937","display_name":"S\u00e9bastien Limet","orcid":null},"institutions":[{"id":"https://openalex.org/I12449238","display_name":"Universit\u00e9 d'Orl\u00e9ans","ror":"https://ror.org/014zrew76","country_code":"FR","type":"education","lineage":["https://openalex.org/I12449238"]},{"id":"https://openalex.org/I4387153997","display_name":"Laboratoire d'Informatique Fondamentale d'Orl\u00e9ans","ror":"https://ror.org/01nr3td38","country_code":null,"type":"facility","lineage":["https://openalex.org/I12449238","https://openalex.org/I4210143826","https://openalex.org/I4387153997"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"S\u00e9bastien Limet","raw_affiliation_strings":["Universit\u00e9 d\u2019Orl\u00e9ans, Orl\u00e9ans, France","LIFO - Laboratoire d'Informatique Fondamentale d'Orl\u00e9ans (B\u00e2timent IIIA, Rue L\u00e9onard de Vinci, B.P. 6759, F-45067 ORLEANS Cedex 2 - France)"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 d\u2019Orl\u00e9ans, Orl\u00e9ans, France","institution_ids":["https://openalex.org/I12449238"]},{"raw_affiliation_string":"LIFO - Laboratoire d'Informatique Fondamentale d'Orl\u00e9ans (B\u00e2timent IIIA, Rue L\u00e9onard de Vinci, B.P. 6759, F-45067 ORLEANS Cedex 2 - France)","institution_ids":["https://openalex.org/I4387153997"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053667707","display_name":"Massimo Torquati","orcid":"https://orcid.org/0000-0001-6323-3459"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Massimo Torquati","raw_affiliation_strings":["Computer Science Department, University of Pisa, Pisa, Italy","University of Pisa - Universit\u00e0 di Pisa (Lungarno Pacinotti 43 - 56126 Pisa - Italy)"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Pisa, Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]},{"raw_affiliation_string":"University of Pisa - Universit\u00e0 di Pisa (Lungarno Pacinotti 43 - 56126 Pisa - Italy)","institution_ids":["https://openalex.org/I108290504"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5071107206"],"corresponding_institution_ids":["https://openalex.org/I108290504"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06428589,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"52","issue":"3","first_page":"207","last_page":"230"},"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":0.9990000128746033,"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":0.9990000128746033,"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":0.9872000217437744,"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/T11269","display_name":"Algorithms and Data Compression","score":0.982699990272522,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9036515951156616},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.6959320902824402},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6170205473899841},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.6111147999763489},{"id":"https://openalex.org/keywords/serialization","display_name":"Serialization","score":0.5981886386871338},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5380818843841553},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5295456647872925},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.5247007608413696},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.516019344329834},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.4925857186317444},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.4523147940635681},{"id":"https://openalex.org/keywords/theory-of-computation","display_name":"Theory of computation","score":0.4445784389972687},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3958476185798645},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.3356984853744507},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23439708352088928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1397165060043335},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10906746983528137},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10510402917861938}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9036515951156616},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.6959320902824402},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6170205473899841},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.6111147999763489},{"id":"https://openalex.org/C52723943","wikidata":"https://www.wikidata.org/wiki/Q1127410","display_name":"Serialization","level":2,"score":0.5981886386871338},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5380818843841553},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5295456647872925},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.5247007608413696},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.516019344329834},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.4925857186317444},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.4523147940635681},{"id":"https://openalex.org/C24858836","wikidata":"https://www.wikidata.org/wiki/Q844718","display_name":"Theory of computation","level":2,"score":0.4445784389972687},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3958476185798645},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.3356984853744507},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23439708352088928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1397165060043335},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10906746983528137},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10510402917861938},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s10766-024-00772-1","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1007/s10766-024-00772-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10766-024-00772-1.pdf","source":{"id":"https://openalex.org/S148521650","display_name":"International Journal of Parallel Programming","issn_l":"0885-7458","issn":["0885-7458","1573-7640"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Parallel Programming","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-04575238v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04575238","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"16TH INTERNATIONAL SYMPOSIUM ON HIGH-LEVEL PARALLEL PROGRAMMING AND APPLICATIONS, Jun 2023, Cluj-Napoca, Romania","raw_type":"Conference papers"},{"id":"pmh:oai:HAL:hal-04586759v1","is_oa":false,"landing_page_url":"https://univ-orleans.hal.science/hal-04586759","pdf_url":null,"source":{"id":"https://openalex.org/S4406922466","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal of Parallel Programming, 2024, &#x27E8;10.1007/s10766-024-00772-1&#x27E9;","raw_type":"Journal articles"},{"id":"pmh:oai:arpi.unipi.it:11568/1282175","is_oa":false,"landing_page_url":"https://hdl.handle.net/11568/1282175","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"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":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s10766-024-00772-1","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1007/s10766-024-00772-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10766-024-00772-1.pdf","source":{"id":"https://openalex.org/S148521650","display_name":"International Journal of Parallel Programming","issn_l":"0885-7458","issn":["0885-7458","1573-7640"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Parallel Programming","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.44999998807907104}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324499","display_name":"Universit\u00e0 di Pisa","ror":"https://ror.org/03ad39j10"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4398250068.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1969186495","https://openalex.org/W1971267250","https://openalex.org/W1987562803","https://openalex.org/W1996940846","https://openalex.org/W2012976560","https://openalex.org/W2030079560","https://openalex.org/W2058209638","https://openalex.org/W2086322024","https://openalex.org/W2097776316","https://openalex.org/W2107096626","https://openalex.org/W2109803107","https://openalex.org/W2121516976","https://openalex.org/W2124299914","https://openalex.org/W2147717514","https://openalex.org/W2152565070","https://openalex.org/W2160694821","https://openalex.org/W2173213060","https://openalex.org/W2256063247","https://openalex.org/W2314960367","https://openalex.org/W2336894004","https://openalex.org/W2542459869","https://openalex.org/W2593611378","https://openalex.org/W2597017779","https://openalex.org/W2612210001","https://openalex.org/W2618516564","https://openalex.org/W2619987598","https://openalex.org/W2805701404","https://openalex.org/W2883952940","https://openalex.org/W2915832966","https://openalex.org/W2938070826","https://openalex.org/W2965708114","https://openalex.org/W3029266587","https://openalex.org/W3082524322","https://openalex.org/W3158334837","https://openalex.org/W3160289844","https://openalex.org/W3194838959","https://openalex.org/W4246338008","https://openalex.org/W4281388628","https://openalex.org/W4281554285","https://openalex.org/W4311119683","https://openalex.org/W6600137863"],"related_works":["https://openalex.org/W2135779989","https://openalex.org/W2963940951","https://openalex.org/W4300633212","https://openalex.org/W2796483994","https://openalex.org/W2608731915","https://openalex.org/W2144265691","https://openalex.org/W2754607325","https://openalex.org/W144856782","https://openalex.org/W2080135560","https://openalex.org/W2147226516"],"abstract_inverted_index":{"Abstract":[0],"Similarity":[1],"joins":[2],"are":[3],"recognized":[4],"to":[5,30,45,55,98],"be":[6,65],"among":[7],"the":[8,32,46,57,85,108,116,120,124,130,145],"most":[9],"used":[10,66],"data":[11,71],"processing":[12],"and":[13,73,77,92,94,101,156],"analysis":[14],"operations.":[15],"We":[16,80],"introduce":[17],"a":[18,138,150],"C++-based":[19],"high-level":[20],"parallel":[21,62],"pattern":[22,41,63,110],"implemented":[23,43],"on":[24,75],"top":[25],"of":[26,84,107,129],"FastFlow":[27],"Building":[28],"Blocks":[29],"provide":[31],"programmer":[33],"with":[34,50,67],"ready-to-use":[35],"similarity":[36,132],"join":[37,133],"computations.":[38],"The":[39,60,104,141],"SimilarityJoin":[40,109,146],"is":[42,160],"according":[44],"MapReduce":[47],"paradigm":[48],"enriched":[49],"locality":[51],"sensitive":[52],"hashing":[53],"(LSH)":[54],"optimize":[56],"whole":[58],"computation.":[59],"new":[61],"can":[64],"any":[68],"C++":[69],"serializable":[70],"structure":[72],"executed":[74],"shared-":[76],"distributed-memory":[78],"machines.":[79],"present":[81],"experimental":[82],"validations":[83],"proposed":[86],"solution":[87],"considering":[88],"two":[89],"different":[90],"clusters":[91],"small":[93,155],"large":[95,166],"input":[96,167],"datasets":[97,168],"evaluate":[99],"in-core":[100],"out-of-core":[102,170],"executions.":[103,171],"performance":[105,152],"assessment":[106],"has":[111],"been":[112],"conducted":[113],"by":[114],"comparing":[115],"execution":[117],"time":[118],"against":[119],"one":[121],"obtained":[122],"from":[123],"original":[125],"hand-tuned":[126],"Hadoop-based":[127],"implementation":[128],"LSH-based":[131],"algorithms":[134],"as":[135,137],"well":[136],"Spark-based":[139],"version.":[140],"experiments":[142],"show":[143],"that":[144],"pattern:":[147],"(1)":[148],"offers":[149],"significant":[151],"improvement":[153],"for":[154,163],"medium":[157],"datasets;":[158],"(2)":[159],"competitive":[161],"also":[162],"computations":[164],"using":[165],"producing":[169]},"counts_by_year":[],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}
