{"id":"https://openalex.org/W4416960645","doi":"https://doi.org/10.1109/tpami.2025.3639635","title":"FedFask: Fast Sketching Distributed PCA for Large-Scale Federated Data","display_name":"FedFask: Fast Sketching Distributed PCA for Large-Scale Federated Data","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4416960645","doi":"https://doi.org/10.1109/tpami.2025.3639635","pmid":"https://pubmed.ncbi.nlm.nih.gov/41336158"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3639635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3639635","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5059740341","display_name":"Xingcai Zhou","orcid":"https://orcid.org/0000-0001-9108-530X"},"institutions":[{"id":"https://openalex.org/I206777745","display_name":"Nanjing Audit University","ror":"https://ror.org/04zj2bd87","country_code":"CN","type":"education","lineage":["https://openalex.org/I206777745"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xingcai Zhou","raw_affiliation_strings":["School of Statistics and Data Science and Joint Lab for Statistics and Finance, Nanjing Audit University, Nanjing, China","School of Statistics and Data Science and Joint Lab for Statistics and Finance, Nanjing Audit University, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"School of Statistics and Data Science and Joint Lab for Statistics and Finance, Nanjing Audit University, Nanjing, China","institution_ids":["https://openalex.org/I206777745"]},{"raw_affiliation_string":"School of Statistics and Data Science and Joint Lab for Statistics and Finance, Nanjing Audit University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I206777745"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436471","display_name":"Guang Yang","orcid":"https://orcid.org/0000-0002-9213-2953"},"institutions":[{"id":"https://openalex.org/I206777745","display_name":"Nanjing Audit University","ror":"https://ror.org/04zj2bd87","country_code":"CN","type":"education","lineage":["https://openalex.org/I206777745"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guang Yang","raw_affiliation_strings":["School of Statistics and Data Science and Joint Lab for Statistics and Finance, Nanjing Audit University, Nanjing, China","School of Statistics and Data Science and Joint Lab for Statistics and Finance, Nanjing Audit University, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"School of Statistics and Data Science and Joint Lab for Statistics and Finance, Nanjing Audit University, Nanjing, China","institution_ids":["https://openalex.org/I206777745"]},{"raw_affiliation_string":"School of Statistics and Data Science and Joint Lab for Statistics and Finance, Nanjing Audit University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I206777745"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101919814","display_name":"Haotian Zheng","orcid":"https://orcid.org/0009-0004-0729-4491"},"institutions":[{"id":"https://openalex.org/I206777745","display_name":"Nanjing Audit University","ror":"https://ror.org/04zj2bd87","country_code":"CN","type":"education","lineage":["https://openalex.org/I206777745"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haotian Zheng","raw_affiliation_strings":["School of Statistics and Data Science and Joint Lab for Statistics and Finance, Nanjing Audit University, Nanjing, China","School of Statistics and Data Science and Joint Lab for Statistics and Finance, Nanjing Audit University, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"School of Statistics and Data Science and Joint Lab for Statistics and Finance, Nanjing Audit University, Nanjing, China","institution_ids":["https://openalex.org/I206777745"]},{"raw_affiliation_string":"School of Statistics and Data Science and Joint Lab for Statistics and Finance, Nanjing Audit University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I206777745"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062334200","display_name":"Linglong Kong","orcid":"https://orcid.org/0000-0003-3011-9216"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Linglong Kong","raw_affiliation_strings":["Department of Mathematical and Statistical Sciences, University of Alberta, Edmonton, AB, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Mathematical and Statistical Sciences, University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017808266","display_name":"Jinde Cao","orcid":"https://orcid.org/0000-0003-3133-7119"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinde Cao","raw_affiliation_strings":["School of Mathematics, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Mathematics, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5059740341"],"corresponding_institution_ids":["https://openalex.org/I206777745"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20415838,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"3","first_page":"3714","last_page":"3725"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.4388999938964844,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.4388999938964844,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.40230000019073486,"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/T11716","display_name":"Random Matrices and Applications","score":0.054999999701976776,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.6599000096321106},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.636900007724762},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.6182000041007996},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.5810999870300293},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5371000170707703},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5038999915122986},{"id":"https://openalex.org/keywords/stiefel-manifold","display_name":"Stiefel manifold","score":0.46399998664855957},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.4575999975204468},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.4287000000476837},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4120999872684479}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.744700014591217},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.6599000096321106},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.636900007724762},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.6182000041007996},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.5810999870300293},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5371000170707703},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5038999915122986},{"id":"https://openalex.org/C612670","wikidata":"https://www.wikidata.org/wiki/Q7616373","display_name":"Stiefel manifold","level":2,"score":0.46399998664855957},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.4575999975204468},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.43779999017715454},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.4287000000476837},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4120999872684479},{"id":"https://openalex.org/C179145077","wikidata":"https://www.wikidata.org/wiki/Q5154130","display_name":"Communication complexity","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3847000002861023},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3815999925136566},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.37380000948905945},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.3553999960422516},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3330000042915344},{"id":"https://openalex.org/C49555168","wikidata":"https://www.wikidata.org/wiki/Q176583","display_name":"Stochastic matrix","level":3,"score":0.33239999413490295},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C151876577","wikidata":"https://www.wikidata.org/wiki/Q7049464","display_name":"Nonlinear dimensionality reduction","level":3,"score":0.30239999294281006},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.3021000027656555},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C92207270","wikidata":"https://www.wikidata.org/wiki/Q939253","display_name":"Matrix norm","level":3,"score":0.2890999913215637},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C144559511","wikidata":"https://www.wikidata.org/wiki/Q2986279","display_name":"Principal (computer security)","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C2778585274","wikidata":"https://www.wikidata.org/wiki/Q2845240","display_name":"Procrustes analysis","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C103275481","wikidata":"https://www.wikidata.org/wiki/Q6787889","display_name":"Matrix representation","level":3,"score":0.26930001378059387},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26739999651908875},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.2630000114440918},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3639635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3639635","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41336158","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41336158","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1978494516","https://openalex.org/W1994938797","https://openalex.org/W2018199316","https://openalex.org/W2021661079","https://openalex.org/W2035076036","https://openalex.org/W2097714737","https://openalex.org/W2117756735","https://openalex.org/W2279901945","https://openalex.org/W2615253071","https://openalex.org/W2964242436","https://openalex.org/W2982674132","https://openalex.org/W3021654819","https://openalex.org/W3126428072","https://openalex.org/W3202260564","https://openalex.org/W3203712890","https://openalex.org/W4238805501","https://openalex.org/W4312258136","https://openalex.org/W4402888905","https://openalex.org/W4404788593","https://openalex.org/W4407448552"],"related_works":[],"abstract_inverted_index":{"We":[0,44,140,169],"study":[1],"distributed":[2],"principal":[3],"component":[4],"analysis":[5],"(PCA)":[6],"for":[7,53],"large-scale":[8],"federated":[9],"data":[10,25],"when":[11],"the":[12,69,75,81,135,146,155,175],"sample":[13],"size":[14],"$n$n":[15],"and":[16,41,61,87,96,108,125,133,161],"dimension":[17,82],"$d$d":[18],"are":[19],"both":[20],"ultra-large.":[21],"This":[22],"type":[23],"of":[24,71,77,83,128,138,149,177],"is":[26,68,74,80],"currently":[27],"very":[28],"common,":[29],"but":[30],"faces":[31],"numerous":[32],"challenges":[33],"in":[34],"PCA":[35,157],"learning,":[36],"such":[37,99],"as":[38,100,154],"communication":[39,58],"overhead":[40],"computational":[42,63],"complexity.":[43],"develop":[45,97],"a":[46,119],"new":[47],"algorithm":[48],"${\\mathsf":[49,92,116,143,178],"{FedFask}}$FedFask":[50,117,144],"(Fast":[51],"Sketching":[52],"Federated":[54],"learning)":[55],"with":[56,104],"lower":[57,62,122],"cost":[59],"$O(dr)$O(dr)":[60],"complexity":[64],"$O(d(np/m+p^{2}+r^{2}))$O(d(np/m+p2+r2)),":[65],"where":[66],"$m$m":[67],"number":[70],"workers,":[72],"$r$r":[73],"rank":[76],"matrix,":[78],"$p$p":[79],"sketched":[84],"column":[85],"space,":[86],"$r\\leq":[88],"p\\ll":[89],"d$r\u2264p\u226ad.":[90],"In":[91],"{FedFask}}$FedFask,":[93],"we":[94],"adopt":[95],"technologies":[98],"fast":[101],"sketching,":[102],"alignments":[103],"orthogonal":[105,136],"Procrustes":[106],"Fixing,":[107],"matrix":[109],"Stiefel":[110],"manifold":[111],"via":[112],"Kolmogorov-Nagumo-type":[113],"average.":[114],"Thus,":[115],"has":[118],"higher":[120],"accuracy,":[121],"stochastic":[123],"variation,":[124],"best":[126],"representation":[127],"multiple":[129],"randomly":[130],"projected":[131],"eigenspaces,":[132],"avoids":[134],"ambiguity":[137],"eigenspaces.":[139],"show":[141],"that":[142],"achieves":[145],"same":[147],"rate":[148],"learning":[150],"$O\\left(\\frac{\\kappa":[151],"_{r}r}{\\lambda":[152],"_{r}}\\sqrt{\\frac{r^{*}}{n}}\\right)$O\u03barr\u03bbrr*n":[153],"centralized":[156],"uses":[158],"all":[159],"data,":[160],"tolerates":[162],"more":[163],"workers":[164],"to":[165,173],"parallel":[166],"acceleration":[167],"computation.":[168],"conduct":[170],"extensive":[171],"experiments":[172],"demonstrate":[174],"effectiveness":[176],"{FedFask}}$FedFask.":[179]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-03T00:00:00"}