{"id":"https://openalex.org/W2807044585","doi":"https://doi.org/10.1109/pdp2018.2018.00094","title":"Clustering Goes Big: CLUBS-P, an Algorithm for Unsupervised Clustering Around Centroids Tailored For Big Data Applications","display_name":"Clustering Goes Big: CLUBS-P, an Algorithm for Unsupervised Clustering Around Centroids Tailored For Big Data Applications","publication_year":2018,"publication_date":"2018-03-01","ids":{"openalex":"https://openalex.org/W2807044585","doi":"https://doi.org/10.1109/pdp2018.2018.00094","mag":"2807044585"},"language":"en","primary_location":{"id":"doi:10.1109/pdp2018.2018.00094","doi":"https://doi.org/10.1109/pdp2018.2018.00094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pdp2018.2018.00094","pdf_url":null,"source":{"id":"https://openalex.org/S4210178956","display_name":"Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)","issn_l":"1066-6192","issn":["1066-6192","2377-5750"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 26th Euromicro International Conference on Parallel, Distributed and Network-based Processing (PDP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5011554149","display_name":"Michele Ianni","orcid":"https://orcid.org/0000-0003-0562-7462","observed_orcids":["https://orcid.org/0000-0003-0562-7462"]},"institutions":[{"id":"https://openalex.org/I45204951","display_name":"University of Calabria","ror":"https://ror.org/02rc97e94","country_code":"IT","type":"education","lineage":["https://openalex.org/I45204951"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Michele Ianni","raw_affiliation_strings":["University of Calabria, Rende, CS, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Calabria, Rende, CS, Italy","institution_ids":["https://openalex.org/I45204951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005904043","display_name":"Elio Masciari","orcid":"https://orcid.org/0000-0002-1778-5321","observed_orcids":["https://orcid.org/0000-0002-1778-5321"]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elio Masciari","raw_affiliation_strings":["UCLA, Los Angeles, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLA, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035469601","display_name":"Giuseppe M. Mazzeo","orcid":"https://orcid.org/0000-0002-4357-259X","observed_orcids":["https://orcid.org/0000-0002-4357-259X"]},"institutions":[{"id":"https://openalex.org/I3005160176","display_name":"Institute for High Performance Computing and Networking","ror":"https://ror.org/04r5fge26","country_code":"IT","type":"facility","lineage":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giuseppe Massimo Mazzeo","raw_affiliation_strings":["ICAR-CNR, Rende, CS, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICAR-CNR, Rende, CS, Italy","institution_ids":["https://openalex.org/I3005160176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113467760","display_name":"Carlo Zaniolo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlo Zaniolo","raw_affiliation_strings":["UCLA, Los Angeles, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLA, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2654,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.51311864,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":95},"biblio":{"volume":"400","issue":null,"first_page":"558","last_page":"561"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.8939999938011169,"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":0.8939999938011169,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.059300001710653305,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.010200000368058681,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/clubs","display_name":"clubs","score":0.9810000061988831},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"hierarchical clustering","score":0.7680000066757202},{"id":"https://openalex.org/keywords/unsupervised-clustering","display_name":"unsupervised clustering","score":0.8100000023841858},{"id":"https://openalex.org/keywords/big-data","display_name":"big data","score":0.6499999761581421},{"id":"https://openalex.org/keywords/distributed-algorithms","display_name":"distributed algorithms","score":0.5910000205039978},{"id":"https://openalex.org/keywords/parallel-clustering","display_name":"parallel clustering","score":0.5400000214576721},{"id":"https://openalex.org/keywords/message-passing","display_name":"message passing","score":0.9160000085830688},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.6510000228881836},{"id":"https://openalex.org/keywords/mapreduce","display_name":"MapReduce","score":0.4729999899864197},{"id":"https://openalex.org/keywords/apache-spark","display_name":"Apache Spark","score":0.847000002861023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8499534130096436},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7798988819122314},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7620404958724976},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7395513653755188},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.6910728216171265},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4938283860683441},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.49369415640830994},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42860472202301025},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3798585832118988},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2554909288883209},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.19859400391578674},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.132308691740036},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/pdp2018.2018.00094","doi":"https://doi.org/10.1109/pdp2018.2018.00094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pdp2018.2018.00094","pdf_url":null,"source":{"id":"https://openalex.org/S4210178956","display_name":"Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)","issn_l":"1066-6192","issn":["1066-6192","2377-5750"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 26th Euromicro International Conference on Parallel, Distributed and Network-based Processing (PDP)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unical.it:20.500.11770/328609","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11770/328609","pdf_url":null,"source":{"id":"https://openalex.org/S4377196898","display_name":"Archive of Doctoral Theses and Digital Collections (University of Calabria)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I45204951","host_organization_name":"University of Calabria","host_organization_lineage":["https://openalex.org/I45204951"],"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/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W79970639","https://openalex.org/W1521624597","https://openalex.org/W1576908612","https://openalex.org/W2084846987","https://openalex.org/W2111407801","https://openalex.org/W2124200646","https://openalex.org/W2165093166","https://openalex.org/W2514947471","https://openalex.org/W2593620947","https://openalex.org/W6631138889"],"related_works":["https://openalex.org/W2887700685","https://openalex.org/W2869113556","https://openalex.org/W2965768238","https://openalex.org/W4410461739","https://openalex.org/W2065306205","https://openalex.org/W2791746273","https://openalex.org/W2475262020","https://openalex.org/W1549024380","https://openalex.org/W3092561083","https://openalex.org/W2116762767"],"abstract_inverted_index":{"The":[0],"need":[1],"to":[2,80,102],"support":[3],"advanced":[4],"analytics":[5],"on":[6,46,106,127],"Big":[7],"Data":[8],"is":[9],"driving":[10],"data":[11,37],"scientist'":[12],"interest":[13],"toward":[14],"massively":[15],"parallel":[16,116],"distributed":[17,84],"systems":[18],"and":[19,26,94],"software":[20],"platforms,":[21],"such":[22,47],"as":[23],"Map-":[24],"Reduce":[25],"Spark,":[27],"that":[28,55,66],"make":[29],"possible":[30],"their":[31,42],"scalable":[32,44],"utilization.":[33],"However,":[34],"when":[35],"complex":[36,108],"mining":[38],"algorithms":[39,62],"are":[40],"required,":[41],"fully":[43],"deployment":[45],"platforms":[48],"faces":[49],"a":[50,71,97,115],"number":[51],"of":[52,60,118],"technical":[53],"challenges":[54],"grow":[56],"with":[57,122],"the":[58,61,83,107],"complexity":[59],"involved.":[63],"Thus":[64],"algorithms,":[65],"were":[67],"originally":[68],"designed":[69],"for":[70],"sequential":[72],"nature,":[73],"must":[74],"often":[75],"be":[76,103],"redesigned":[77],"in":[78],"order":[79],"effectively":[81],"use":[82],"computational":[85],"resources.":[86],"In":[87],"this":[88],"paper,":[89],"we":[90],"explore":[91],"these":[92],"problems,":[93],"then":[95],"propose":[96],"solution":[98],"which":[99],"has":[100],"proven":[101],"very":[104],"effective":[105],"hierarchical":[109],"clustering":[110],"algorithm":[111],"CLUBS+.":[112],"We":[113],"present":[114],"version":[117],"CLUBS+":[119],"named":[120],"CLUBS-P":[121],"an":[123],"ad-hoc":[124],"implementation":[125],"based":[126],"message":[128],"passing:":[129],"CLUBS-MP.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-10-27T15:51:10.671819","created_date":"2018-06-13T00:00:00"}