{"id":"https://openalex.org/W2079885973","doi":"https://doi.org/10.1145/2723372.2751520","title":"sPCA","display_name":"sPCA","publication_year":2015,"publication_date":"2015-05-27","ids":{"openalex":"https://openalex.org/W2079885973","doi":"https://doi.org/10.1145/2723372.2751520","mag":"2079885973"},"language":"en","primary_location":{"id":"doi:10.1145/2723372.2751520","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2723372.2751520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data","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/A5056105451","display_name":"Tarek Elgamal","orcid":null},"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":"Tarek Elgamal","raw_affiliation_strings":["Qatar Computing Research Institute, Doha, Qatar","Qatar Computing Research Institute [Doha, Qatar]"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]},{"raw_affiliation_string":"Qatar Computing Research Institute [Doha, Qatar]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035570800","display_name":"Maysam Yabandeh","orcid":null},"institutions":[{"id":"https://openalex.org/I113979032","display_name":"Twitter (United States)","ror":"https://ror.org/04wt43v05","country_code":"US","type":"company","lineage":["https://openalex.org/I113979032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maysam Yabandeh","raw_affiliation_strings":["Twitter, San Francisco, CA, USA","[Twitter, San Francisco, CA, USA]"],"affiliations":[{"raw_affiliation_string":"Twitter, San Francisco, CA, USA","institution_ids":["https://openalex.org/I113979032"]},{"raw_affiliation_string":"[Twitter, San Francisco, CA, USA]","institution_ids":["https://openalex.org/I113979032"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000416532","display_name":"Ashraf Aboulnaga","orcid":"https://orcid.org/0000-0001-6693-7099"},"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":false,"raw_author_name":"Ashraf Aboulnaga","raw_affiliation_strings":["Qatar Computing Research Institute, Doha, Qatar","Qatar Computing Research Institute [Doha, Qatar]"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]},{"raw_affiliation_string":"Qatar Computing Research Institute [Doha, Qatar]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025136847","display_name":"Waleed Mustafa","orcid":"https://orcid.org/0000-0002-7905-8605"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Waleed Mustafa","raw_affiliation_strings":["NTG Clarity, Cairo, Egypt"],"affiliations":[{"raw_affiliation_string":"NTG Clarity, Cairo, Egypt","institution_ids":[]}]},{"author_position":"last","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":false,"raw_author_name":"Mohamed Hefeeda","raw_affiliation_strings":["Qatar Computing Research Institute, Doha, Qatar","Qatar Computing Research Institute [Doha, Qatar]"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]},{"raw_affiliation_string":"Qatar Computing Research Institute [Doha, Qatar]","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5056105451"],"corresponding_institution_ids":["https://openalex.org/I1301390666"],"apc_list":null,"apc_paid":null,"fwci":4.2342,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.96189407,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"79","last_page":"91"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9951000213623047,"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":0.9951000213623047,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9887999892234802,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9879000186920166,"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":0.8384047746658325},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7671303153038025},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.756693959236145},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.7034014463424683},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.6983579397201538},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5012710094451904},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4912559390068054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4748563766479492},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4672505855560303},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4582386016845703},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4368484318256378},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3222726583480835},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.16281893849372864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8384047746658325},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7671303153038025},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.756693959236145},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.7034014463424683},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.6983579397201538},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5012710094451904},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4912559390068054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4748563766479492},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4672505855560303},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4582386016845703},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4368484318256378},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3222726583480835},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.16281893849372864},{"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:10.1145/2723372.2751520","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2723372.2751520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W31634058","https://openalex.org/W94439627","https://openalex.org/W262970172","https://openalex.org/W568124517","https://openalex.org/W749579920","https://openalex.org/W1545533962","https://openalex.org/W1964455610","https://openalex.org/W1975900269","https://openalex.org/W1976860187","https://openalex.org/W2013344760","https://openalex.org/W2049633694","https://openalex.org/W2068410942","https://openalex.org/W2072773380","https://openalex.org/W2077166865","https://openalex.org/W2078841894","https://openalex.org/W2099242680","https://openalex.org/W2102458936","https://openalex.org/W2108598243","https://openalex.org/W2109722477","https://openalex.org/W2121195096","https://openalex.org/W2124386111","https://openalex.org/W2131975293","https://openalex.org/W2138243089","https://openalex.org/W2146610201","https://openalex.org/W2148694408","https://openalex.org/W2158548804","https://openalex.org/W2173213060","https://openalex.org/W2184623761","https://openalex.org/W2270190912","https://openalex.org/W2403401779","https://openalex.org/W2951781666","https://openalex.org/W4292023222","https://openalex.org/W6609634455","https://openalex.org/W6676367512","https://openalex.org/W6686239164"],"related_works":["https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W2347335694","https://openalex.org/W3202731209","https://openalex.org/W4250857377","https://openalex.org/W4240326769","https://openalex.org/W3211874991","https://openalex.org/W3012518171","https://openalex.org/W2906268655","https://openalex.org/W2844620057"],"abstract_inverted_index":{"Web":[0],"sites,":[1],"social":[2],"networks,":[3],"sensors,":[4],"and":[5,95,124,136,157,167,178],"scientific":[6],"experiments":[7,160],"currently":[8],"generate":[9],"massive":[10],"amounts":[11],"of":[12,15,46,174,180],"data.":[13,47,127],"Owners":[14],"this":[16,50],"data":[17,91,182],"strive":[18],"to":[19,39,72,100],"obtain":[20],"insights":[21],"from":[22],"it,":[23],"often":[24],"by":[25,169],"applying":[26],"machine":[27,31,62],"learning":[28,32,63],"algorithms.":[29],"Many":[30],"algorithms,":[33],"however,":[34],"do":[35],"not":[36],"scale":[37],"well":[38],"cope":[40],"with":[41],"the":[42,73,101,132,138,146,152,185],"ever":[43],"increasing":[44],"volumes":[45],"To":[48],"address":[49],"problem,":[51],"we":[52],"identify":[53],"several":[54],"optimizations":[55,71],"that":[56,162],"are":[57,151],"crucial":[58],"for":[59],"scaling":[60],"various":[61],"algorithms":[64],"in":[65,85,154,172],"distributed":[66],"settings.":[67],"We":[68,98,128,142],"apply":[69],"these":[70],"popular":[74],"Principal":[75],"Component":[76],"Analysis":[77],"(PCA)":[78],"algorithm.":[79],"PCA":[80,104,148],"is":[81],"an":[82],"important":[83],"tool":[84],"many":[86],"areas":[87],"including":[88],"image":[89],"processing,":[90],"visualization,":[92],"information":[93],"retrieval,":[94],"dimensionality":[96],"reduction.":[97],"refer":[99],"proposed":[102],"optimized":[103],"algorithm":[105],"as":[106],"scalable":[107],"PCA,":[108],"or":[109],"sPCA.":[110],"sPCA":[111,130,144,163],"achieves":[112],"scalability":[113],"via":[114],"employing":[115],"efficient":[116],"large":[117],"matrix":[118,122],"operations,":[119],"effectively":[120],"leveraging":[121],"sparsity,":[123],"minimizing":[125],"intermediate":[126,181],"implement":[129],"on":[131,137],"widely-used":[133],"MapReduce":[134,156],"platform":[135],"memory-based":[139],"Spark":[140],"platform.":[141],"compare":[143],"against":[145],"closest":[147],"implementations,":[149],"which":[150],"ones":[153],"Mahout/":[155],"MLlib/Spark.":[158],"Our":[159],"show":[161],"outperforms":[164],"both":[165],"Mahout-PCA":[166],"MLlib-PCA":[168],"wide":[170],"margins":[171],"terms":[173],"accuracy,":[175],"running":[176],"time,":[177],"volume":[179],"generated":[183],"during":[184],"computation.":[186]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}