{"id":"https://openalex.org/W2885708503","doi":"https://doi.org/10.1109/bigdata.2018.8622026","title":"Efficient Principal Subspace Projection of Streaming Data Through Fast Similarity Matching","display_name":"Efficient Principal Subspace Projection of Streaming Data Through Fast Similarity Matching","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2885708503","doi":"https://doi.org/10.1109/bigdata.2018.8622026","mag":"2885708503"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2018.8622026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big 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/A5054296113","display_name":"Andrea Giovannucci","orcid":"https://orcid.org/0000-0002-7850-444X"},"institutions":[{"id":"https://openalex.org/I4210153546","display_name":"Flatiron Health (United States)","ror":"https://ror.org/0508h6p74","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153546"]},{"id":"https://openalex.org/I4387153999","display_name":"Flatiron Institute","ror":"https://ror.org/00sekdz59","country_code":null,"type":"nonprofit","lineage":["https://openalex.org/I4210107338","https://openalex.org/I4387153999"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrea Giovannucci","raw_affiliation_strings":["Center for Computational Biology, Flatiron Institute, New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computational Biology, Flatiron Institute, New York, NY","institution_ids":["https://openalex.org/I4210153546","https://openalex.org/I4387153999"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018787411","display_name":"Victor Minden","orcid":"https://orcid.org/0009-0006-9084-6289"},"institutions":[{"id":"https://openalex.org/I4210153546","display_name":"Flatiron Health (United States)","ror":"https://ror.org/0508h6p74","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153546"]},{"id":"https://openalex.org/I4387153999","display_name":"Flatiron Institute","ror":"https://ror.org/00sekdz59","country_code":null,"type":"nonprofit","lineage":["https://openalex.org/I4210107338","https://openalex.org/I4387153999"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Victor Minden","raw_affiliation_strings":["Center for Computational Biology, Flatiron Institute, New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computational Biology, Flatiron Institute, New York, NY","institution_ids":["https://openalex.org/I4210153546","https://openalex.org/I4387153999"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023195984","display_name":"Cengiz Pehlevan","orcid":"https://orcid.org/0000-0001-9767-6063"},"institutions":[{"id":"https://openalex.org/I4210153546","display_name":"Flatiron Health (United States)","ror":"https://ror.org/0508h6p74","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153546"]},{"id":"https://openalex.org/I4387153999","display_name":"Flatiron Institute","ror":"https://ror.org/00sekdz59","country_code":null,"type":"nonprofit","lineage":["https://openalex.org/I4210107338","https://openalex.org/I4387153999"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cengiz Pehlevan","raw_affiliation_strings":["Center for Computational Biology, Flatiron Institute, New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computational Biology, Flatiron Institute, New York, NY","institution_ids":["https://openalex.org/I4210153546","https://openalex.org/I4387153999"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062874541","display_name":"Dmitri B. Chklovskii","orcid":"https://orcid.org/0000-0002-4781-2546"},"institutions":[{"id":"https://openalex.org/I4210086933","display_name":"NYU Langone Health","ror":"https://ror.org/005dvqh91","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210086933"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dmitri B. Chklovskii","raw_affiliation_strings":["Neuroscience Institute, NYU Langone Medical Center, New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Neuroscience Institute, NYU Langone Medical Center, New York, NY","institution_ids":["https://openalex.org/I4210086933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1827,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84395216,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9902999997138977,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9902999997138977,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9894000291824341,"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":0.7996212840080261},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.6718319058418274},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5945261716842651},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5692943334579468},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5567578077316284},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5162120461463928},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5145716071128845},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5106692910194397},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.49515214562416077},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.47863855957984924},{"id":"https://openalex.org/keywords/random-projection","display_name":"Random projection","score":0.45890870690345764},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.45175233483314514},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3328743577003479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3160274028778076},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1092139482498169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7996212840080261},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.6718319058418274},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5945261716842651},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5692943334579468},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5567578077316284},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5162120461463928},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5145716071128845},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5106692910194397},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.49515214562416077},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.47863855957984924},{"id":"https://openalex.org/C2777036070","wikidata":"https://www.wikidata.org/wiki/Q18393452","display_name":"Random projection","level":2,"score":0.45890870690345764},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.45175233483314514},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3328743577003479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3160274028778076},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1092139482498169},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2018.8622026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6499999761581421}],"awards":[],"funders":[{"id":"https://openalex.org/F4320336163","display_name":"Institute of Psychology, Chinese Academy of Sciences","ror":"https://ror.org/03j7v5j15"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1278167707","https://openalex.org/W1520752838","https://openalex.org/W1555711139","https://openalex.org/W1566234743","https://openalex.org/W1981745143","https://openalex.org/W2009642296","https://openalex.org/W2010464263","https://openalex.org/W2110121428","https://openalex.org/W2112796928","https://openalex.org/W2131329059","https://openalex.org/W2133515443","https://openalex.org/W2139182243","https://openalex.org/W2140984045","https://openalex.org/W2141681031","https://openalex.org/W2142075335","https://openalex.org/W2154249783","https://openalex.org/W2169548727","https://openalex.org/W2294798173","https://openalex.org/W2333315597","https://openalex.org/W2432567885","https://openalex.org/W2555690212","https://openalex.org/W2735683573","https://openalex.org/W2964163643","https://openalex.org/W3102303919","https://openalex.org/W6676539569","https://openalex.org/W6681209497","https://openalex.org/W6702811211"],"related_works":["https://openalex.org/W1995622179","https://openalex.org/W2790862734","https://openalex.org/W3125756894","https://openalex.org/W1552543208","https://openalex.org/W345943785","https://openalex.org/W2074396517","https://openalex.org/W2166963679","https://openalex.org/W2187269125","https://openalex.org/W2141406155","https://openalex.org/W1641615907"],"abstract_inverted_index":{"Big":[0],"data":[1,14,29,33,70,102],"problems":[2],"frequently":[3],"require":[4],"processing":[5],"datasets":[6],"in":[7,73],"a":[8,36,46,54,95,100],"streaming":[9],"fashion,":[10],"either":[11],"because":[12,27],"all":[13],"are":[15,21],"available":[16,24],"at":[17,35],"once":[18],"but":[19],"collectively":[20],"larger":[22],"than":[23],"memory":[25,74],"or":[26],"the":[28,63,76,80,85,105,131,143],"intrinsically":[30],"arrive":[31],"one":[32],"point":[34],"time":[37],"and":[38,79,92,104,124,148],"must":[39],"be":[40,139],"processed":[41],"online.":[42],"Here,":[43],"we":[44,90,134],"introduce":[45],"computationally":[47],"efficient":[48],"version":[49],"of":[50,68,87,121],"similarity":[51],"matching":[52],"[1],":[53],"framework":[55],"for":[56],"online":[57,109],"dimensionality":[58,110],"reduction":[59,111],"that":[60],"incrementally":[61],"estimates":[62],"top":[64],"K-dimensional":[65],"principal":[66],"subspace":[67],"streamed":[69],"while":[71],"keeping":[72],"only":[75],"last":[77],"sample":[78],"current":[81],"iterate.":[82],"To":[83],"assess":[84],"performance":[86],"our":[88,122,136],"approach,":[89],"construct":[91],"make":[93],"public":[94],"test":[96,108],"suite":[97],"containing":[98],"both":[99,146],"synthetic":[101,147],"generator":[103],"infrastructure":[106],"to":[107,138],"algorithms":[112,126,132],"on":[113,145],"real":[114,149],"datasets,":[115],"as":[116,118],"well":[117],"performant":[119],"implementations":[120],"algorithm":[123],"competing":[125],"with":[127],"similar":[128],"aims.":[129],"Among":[130],"considered":[133],"find":[135],"approach":[137],"competitive,":[140],"performing":[141],"among":[142],"best":[144],"data.":[150]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}