{"id":"https://openalex.org/W2869113556","doi":"https://doi.org/10.1145/3216122.3216154","title":"Efficient Big Data Clustering","display_name":"Efficient Big Data Clustering","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2869113556","doi":"https://doi.org/10.1145/3216122.3216154","mag":"2869113556"},"language":"en","primary_location":{"id":"doi:10.1145/3216122.3216154","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3216122.3216154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Database Engineering & Applications Symposium on - IDEAS 2018","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/A5011554149","display_name":"Michele Ianni","orcid":"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"},"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":"Elio Masciari","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":"middle","author":{"id":"https://openalex.org/A5035469601","display_name":"Giuseppe M. Mazzeo","orcid":"https://orcid.org/0000-0002-4357-259X"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Giuseppe M. Mazzeo","raw_affiliation_strings":["Facebook, Menlo Park, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook, Menlo Park, USA","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113467760","display_name":"Carlo Zaniolo","orcid":null},"institutions":[{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"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/I2799798094"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"103","last_page":"109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9995999932289124,"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":0.9995999932289124,"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/T11106","display_name":"Data Management and Algorithms","score":0.9966999888420105,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9958999752998352,"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":0.8530115485191345},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8010968565940857},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7777611017227173},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.753450870513916},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6844154596328735},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5278934240341187},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5103926062583923},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4727393388748169},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.454633891582489},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.372742235660553},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.259141206741333},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.23403272032737732},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.16542541980743408},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.15927252173423767}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8530115485191345},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8010968565940857},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7777611017227173},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.753450870513916},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6844154596328735},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5278934240341187},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5103926062583923},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4727393388748169},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.454633891582489},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.372742235660553},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.259141206741333},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.23403272032737732},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.16542541980743408},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.15927252173423767},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3216122.3216154","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3216122.3216154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Database Engineering & Applications Symposium on - IDEAS 2018","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1985059878","https://openalex.org/W2085487226","https://openalex.org/W2104829661","https://openalex.org/W2593620947","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2770234245","https://openalex.org/W96612179","https://openalex.org/W4229499248","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991","https://openalex.org/W4308507533","https://openalex.org/W2407107767"],"abstract_inverted_index":{"The":[0],"need":[1],"to":[2,79,101],"support":[3],"advanced":[4],"analytics":[5],"on":[6,45,105],"Big":[7],"Data":[8],"is":[9],"driving":[10],"data":[11,36,124],"scientist'":[12],"interest":[13],"toward":[14],"massively":[15],"parallel":[16],"distributed":[17,83],"systems":[18],"and":[19,25,93,140],"software":[20],"platforms,":[21],"such":[22,46],"as":[23],"Map-Reduce":[24],"Spark,":[26],"that":[27,54,65],"make":[28],"possible":[29],"their":[30,41,127],"scalable":[31,43],"utilization.":[32],"However,":[33],"when":[34],"complex":[35,107],"mining":[37],"algorithms":[38,61],"are":[39],"required,":[40],"fully":[42],"deployment":[44],"platforms":[47],"faces":[48],"a":[49,70,96,131],"number":[50],"of":[51,59,116,123,142],"technical":[52],"challenges":[53],"grow":[55],"with":[56],"the":[57,60,82,106,138],"complexity":[58],"involved.":[62],"Thus":[63],"algorithms,":[64],"were":[66],"originally":[67],"designed":[68],"for":[69],"sequential":[71],"nature,":[72],"must":[73],"often":[74],"be":[75,102],"redesigned":[76],"in":[77,130],"order":[78],"effectively":[80],"use":[81],"computational":[84],"resources.":[85],"In":[86],"this":[87],"paper,":[88],"we":[89],"explore":[90],"these":[91],"problems,":[92],"then":[94],"propose":[95],"solution":[97],"which":[98],"has":[99],"proven":[100],"very":[103],"effective":[104],"hierarchical":[108],"clustering":[109],"algorithm":[110],"CLUBS+.":[111,143],"By":[112],"using":[113],"four":[114],"stages":[115],"successive":[117],"refinements,":[118],"CLUBS+":[119],"delivers":[120],"high-quality":[121],"clusters":[122],"grouped":[125],"around":[126],"centroids,":[128],"working":[129],"totally":[132],"unsupervised":[133],"fashion.":[134],"Experimental":[135],"results":[136],"confirm":[137],"accuracy":[139],"scalability":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}