{"id":"https://openalex.org/W7157059235","doi":"https://doi.org/10.48550/arxiv.2604.24012","title":"FedSLoP: Memory-Efficient Federated Learning with Low-Rank Gradient Projection","display_name":"FedSLoP: Memory-Efficient Federated Learning with Low-Rank Gradient Projection","publication_year":2026,"publication_date":"2026-04-27","ids":{"openalex":"https://openalex.org/W7157059235","doi":"https://doi.org/10.48550/arxiv.2604.24012"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.24012","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24012","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.24012","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134754704","display_name":"Yutong He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Yutong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134816055","display_name":"Zhengyang Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Zhengyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134788036","display_name":"Jiahe Geng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geng, Jiahe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Yuan, Kun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Kun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.6352999806404114,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.6352999806404114,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.3327000141143799,"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":0.00430000014603138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.8865000009536743},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.6773999929428101},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5138999819755554},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.49309998750686646},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.484499990940094},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.44350001215934753},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.43059998750686646},{"id":"https://openalex.org/keywords/smoothness","display_name":"Smoothness","score":0.42570000886917114},{"id":"https://openalex.org/keywords/random-projection","display_name":"Random projection","score":0.42089998722076416}],"concepts":[{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.8865000009536743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7595999836921692},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.6773999929428101},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5138999819755554},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.49309998750686646},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.484499990940094},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.44350001215934753},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.43059998750686646},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.42570000886917114},{"id":"https://openalex.org/C2777036070","wikidata":"https://www.wikidata.org/wiki/Q18393452","display_name":"Random projection","level":2,"score":0.42089998722076416},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.41659998893737793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38199999928474426},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3756999969482422},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36880001425743103},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3239000141620636},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.30160000920295715},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29580000042915344},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C189237950","wikidata":"https://www.wikidata.org/wiki/Q2500758","display_name":"Stationary point","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.26510000228881836},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2632000148296356},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.24012","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24012","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.24012","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24012","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.42677512764930725}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Federated":[0],"learning":[1,11],"enables":[2],"a":[3,41,72,91,96,154],"population":[4],"of":[5,51,57,98],"clients":[6],"to":[7,88,90,159],"collaboratively":[8],"train":[9],"machine":[10],"models":[12],"without":[13],"exchanging":[14],"their":[15],"raw":[16],"data,":[17],"but":[18],"standard":[19,78],"algorithms":[20],"such":[21,150],"as":[22,151],"FedAvg":[23,134],"suffer":[24],"from":[25],"slow":[26],"convergence":[27,75],"and":[28,31,59,80,123,135,156,161],"high":[29],"communication":[30,121],"memory":[32,125],"costs":[33],"in":[34],"heterogeneous,":[35],"resource-constrained":[36],"environments.":[37],"We":[38],"introduce":[39],"FedSLoP,":[40],"federated":[42,109,163],"optimization":[43,64],"algorithm":[44],"that":[45,84,117,145],"combines":[46],"stochastic":[47],"low-rank":[48,139],"subspace":[49,147],"projections":[50],"gradients,":[52],"thereby":[53],"reducing":[54],"the":[55,67,101],"dimension":[56],"communicated":[58],"stored":[60],"updates":[61],"while":[62,126],"preserving":[63],"progress.":[65],"On":[66,100],"theoretical":[68],"side,":[69,103],"we":[70,104],"develop":[71],"detailed":[73],"nonconvex":[74],"analysis":[76],"under":[77],"smoothness":[79],"bounded-variance":[81],"assumptions,":[82],"showing":[83,116],"FedSLoP":[85,118,152],"is":[86],"guaranteed":[87],"converge":[89],"first-order":[92],"stationary":[93],"point":[94],"at":[95],"rate":[97],"$O(1/\\sqrt{NT})$.":[99],"empirical":[102],"conduct":[105],"extensive":[106],"experiments":[107],"on":[108],"MNIST":[110],"classification":[111],"with":[112,133],"heterogeneous":[113],"data":[114],"partitions,":[115],"substantially":[119],"reduces":[120],"volume":[122],"client-side":[124],"achieving":[127],"competitive":[128],"or":[129,138],"better":[130],"accuracy":[131],"compared":[132],"representative":[136],"sparse":[137],"baselines.":[140],"Together,":[141],"our":[142],"results":[143],"demonstrate":[144],"random":[146],"momentum":[148],"methods":[149],"provide":[153],"principled":[155],"effective":[157],"approach":[158],"communication-":[160],"memory-efficient":[162],"learning.":[164],"Codes":[165],"are":[166],"available":[167],"at:":[168],"https://github.com/pkumelon/FedSLoP.git.":[169]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-29T00:00:00"}