{"id":"https://openalex.org/W2153246527","doi":"https://doi.org/10.1145/2287076.2287111","title":"Distributed approximate spectral clustering for large-scale datasets","display_name":"Distributed approximate spectral clustering for large-scale datasets","publication_year":2012,"publication_date":"2012-06-18","ids":{"openalex":"https://openalex.org/W2153246527","doi":"https://doi.org/10.1145/2287076.2287111","mag":"2153246527"},"language":"en","primary_location":{"id":"doi:10.1145/2287076.2287111","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2287076.2287111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st international symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-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/A5084024266","display_name":"Mohamed Hefeeda","orcid":"https://orcid.org/0000-0003-3261-4376"},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":true,"raw_author_name":"Mohamed Hefeeda","raw_affiliation_strings":["Qatar Computing Research Institute, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001383535","display_name":"Fei Gao","orcid":"https://orcid.org/0000-0002-4678-1936"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Fei Gao","raw_affiliation_strings":["Simon Fraser University, Surrey, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Simon Fraser University, Surrey, BC, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028776484","display_name":"Wael AbdAlmageed","orcid":"https://orcid.org/0000-0002-8320-8530"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wael Abd-Almageed","raw_affiliation_strings":["University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084024266"],"corresponding_institution_ids":["https://openalex.org/I1301390666"],"apc_list":null,"apc_paid":null,"fwci":2.5151,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.90979776,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"223","last_page":"234"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9973000288009644,"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/T10057","display_name":"Face and Expression Recognition","score":0.9973000288009644,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9969000220298767,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9958000183105469,"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":0.8337485790252686},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6580898761749268},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6375340223312378},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6069164872169495},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5804853439331055},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5167112350463867},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.43168339133262634},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4234501123428345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36089855432510376},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.340585857629776},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09508076310157776},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09198054671287537}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8337485790252686},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6580898761749268},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6375340223312378},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6069164872169495},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5804853439331055},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5167112350463867},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.43168339133262634},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4234501123428345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36089855432510376},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.340585857629776},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09508076310157776},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09198054671287537},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2287076.2287111","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2287076.2287111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st international symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5199999809265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":81,"referenced_works":["https://openalex.org/W73454975","https://openalex.org/W146900863","https://openalex.org/W188944072","https://openalex.org/W331646009","https://openalex.org/W603723648","https://openalex.org/W1487115931","https://openalex.org/W1501500081","https://openalex.org/W1506690472","https://openalex.org/W1526146785","https://openalex.org/W1527781663","https://openalex.org/W1555083332","https://openalex.org/W1555915743","https://openalex.org/W1563088657","https://openalex.org/W1573548168","https://openalex.org/W1588861010","https://openalex.org/W1602659231","https://openalex.org/W1672197616","https://openalex.org/W1818277846","https://openalex.org/W1971784203","https://openalex.org/W1977556410","https://openalex.org/W1979848457","https://openalex.org/W1980357388","https://openalex.org/W1981298217","https://openalex.org/W1981556499","https://openalex.org/W1985177823","https://openalex.org/W1994473607","https://openalex.org/W2007901510","https://openalex.org/W2010404145","https://openalex.org/W2012833704","https://openalex.org/W2016332796","https://openalex.org/W2016453697","https://openalex.org/W2028904582","https://openalex.org/W2029197611","https://openalex.org/W2043994139","https://openalex.org/W2051224630","https://openalex.org/W2055141025","https://openalex.org/W2055906546","https://openalex.org/W2066690526","https://openalex.org/W2073415627","https://openalex.org/W2091091431","https://openalex.org/W2091578339","https://openalex.org/W2098006457","https://openalex.org/W2098162425","https://openalex.org/W2101111945","https://openalex.org/W2102593647","https://openalex.org/W2104908641","https://openalex.org/W2111998194","https://openalex.org/W2112545207","https://openalex.org/W2114903718","https://openalex.org/W2116810533","https://openalex.org/W2120665288","https://openalex.org/W2126337883","https://openalex.org/W2126495587","https://openalex.org/W2127498532","https://openalex.org/W2129869373","https://openalex.org/W2130639013","https://openalex.org/W2131229759","https://openalex.org/W2134370969","https://openalex.org/W2140095548","https://openalex.org/W2140539195","https://openalex.org/W2141051095","https://openalex.org/W2141245797","https://openalex.org/W2145349611","https://openalex.org/W2148172987","https://openalex.org/W2154740476","https://openalex.org/W2160167256","https://openalex.org/W2161997479","https://openalex.org/W2164456230","https://openalex.org/W2165232124","https://openalex.org/W2165874743","https://openalex.org/W2167927436","https://openalex.org/W2169446650","https://openalex.org/W2171790913","https://openalex.org/W2173213060","https://openalex.org/W2319660501","https://openalex.org/W2999905431","https://openalex.org/W4254259096","https://openalex.org/W4285719527","https://openalex.org/W6618549861","https://openalex.org/W6684578312","https://openalex.org/W6770641979"],"related_works":["https://openalex.org/W2548059104","https://openalex.org/W2368437561","https://openalex.org/W2348925352","https://openalex.org/W3120511008","https://openalex.org/W3014300295","https://openalex.org/W2383597676","https://openalex.org/W2756322059","https://openalex.org/W1595151633","https://openalex.org/W2064883676","https://openalex.org/W4226091590"],"abstract_inverted_index":{"Data-intensive":[0],"applications":[1],"are":[2,19,37],"becoming":[3],"important":[4,79],"in":[5,16,80,101,115],"many":[6,42,81,181],"science":[7],"and":[8,22,54,103,107,117,126,175,223,244,251],"engineering":[9],"fields,":[10],"because":[11],"of":[12,31,43,134,141,150,167,182,188,196,203,210,214],"the":[13,23,28,44,123,132,135,139,151,154,168,186,189,197,208,215,235],"high":[14,52],"rates":[15],"which":[17,98],"data":[18],"being":[20],"generated":[21],"numerous":[24],"opportunities":[25],"offered":[26],"by":[27],"sheer":[29],"amount":[30],"these":[32],"data.":[33],"Large-scale":[34],"datasets,":[35],"however,":[36],"challenging":[38],"to":[39,50,72,105,121,146],"process":[40,74],"using":[41,257],"current":[45,83],"machine":[46,69,172],"learning":[47,70,173],"algorithms":[48,71,85],"due":[49],"their":[51],"time":[53,102,250],"space":[55,104],"complexities.":[56],"In":[57,137],"this":[58,221],"paper,":[59],"we":[60,192,206],"propose":[61],"a":[62,88,95,194,211],"novel":[63],"approximation":[64,142,190],"algorithm":[65,111,159,200],"that":[66,163,248],"enables":[67],"kernel-based":[68,84,171],"efficiently":[73],"very":[75],"large-scale":[76],"datasets.":[77],"While":[78],"applications,":[82],"suffer":[86],"from":[87],"scalability":[89],"problem":[90],"as":[91,231,233],"they":[92],"require":[93],"computing":[94,156],"kernel":[96,124],"matrix":[97],"takes":[99],"O(N2)":[100],"compute":[106,122],"store.":[108],"The":[109,158],"proposed":[110,216],"yields":[112],"substantial":[113],"reduction":[114],"computation":[116],"memory":[118,252],"overhead":[119],"required":[120,155],"matrix,":[125],"it":[127,164,225],"does":[128],"not":[129],"significantly":[130],"impact":[131],"accuracy":[133,149],"results.":[136],"addition,":[138],"level":[140],"can":[143,177,254],"be":[144,178,255],"controlled":[145],"tradeoff":[147],"some":[148],"results":[152,241],"with":[153,180],"resources.":[157],"is":[160,165],"designed":[161],"such":[162],"independent":[166],"subsequently":[169],"used":[170,179],"algorithm,":[174,191],"thus":[176],"them.":[183],"To":[184],"illustrate":[185],"effect":[187],"developed":[193],"variant":[195],"spectral":[198],"clustering":[199],"on":[201,226,234,242],"top":[202],"it.":[204],"Furthermore,":[205],"present":[207],"design":[209,222],"MapReduce-based":[212],"implementation":[213],"algorithm.":[217,259],"We":[218],"have":[219],"implemented":[220],"run":[224],"our":[227,258],"own":[228],"Hadoop":[229],"cluster":[230],"well":[232],"Amazon":[236],"Elastic":[237],"MapReduce":[238],"service.":[239],"Experimental":[240],"synthetic":[243],"real":[245],"datasets":[246],"demonstrate":[247],"significant":[249],"savings":[253],"achieved":[256]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}