{"id":"https://openalex.org/W4281908558","doi":"https://doi.org/10.48550/arxiv.2205.12493","title":"Federated Self-supervised Learning for Heterogeneous Clients","display_name":"Federated Self-supervised Learning for Heterogeneous Clients","publication_year":2022,"publication_date":"2022-05-25","ids":{"openalex":"https://openalex.org/W4281908558","doi":"https://doi.org/10.48550/arxiv.2205.12493"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2205.12493","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.12493","pdf_url":"https://arxiv.org/pdf/2205.12493","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2205.12493","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015915136","display_name":"Disha Makhija","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Makhija, Disha","raw_affiliation_strings":["University of Texas at Austin ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin ,","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112412955","display_name":"Nhat Ho","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ho, Nhat","raw_affiliation_strings":["University of Texas at Austin ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin ,","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103071668","display_name":"Joydeep Ghosh","orcid":"https://orcid.org/0000-0002-7366-3548","observed_orcids":["https://orcid.org/0000-0002-7366-3548"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ghosh, Joydeep","raw_affiliation_strings":["University of Texas at Austin ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin ,","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":14,"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":0.9990000128746033,"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":0.9990000128746033,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0005000000237487257,"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":9.999999747378752e-05,"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/federated-learning","display_name":"federated learning","score":0.9520000219345093},{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.9980000257492065},{"id":"https://openalex.org/keywords/heterogeneous-clients","display_name":"heterogeneous clients","score":0.7760000228881836},{"id":"https://openalex.org/keywords/system-heterogeneity","display_name":"system heterogeneity","score":0.7839999794960022},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.8460000157356262},{"id":"https://openalex.org/keywords/representation-alignment","display_name":"representation alignment","score":0.6470000147819519},{"id":"https://openalex.org/keywords/convergence-guarantees","display_name":"convergence guarantees","score":0.699999988079071},{"id":"https://openalex.org/keywords/nonconvex-optimization","display_name":"non-convex optimization","score":0.9869999885559082},{"id":"https://openalex.org/keywords/privacy-preserving-machine-learning","display_name":"privacy-preserving machine learning","score":0.7200000286102295},{"id":"https://openalex.org/keywords/limited-labeled-data","display_name":"limited labeled data","score":0.3059999942779541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8312170505523682},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6592249870300293},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.646623432636261},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6125733852386475},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6093679666519165},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5907875299453735},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5501781105995178},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5420530438423157},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5338187217712402},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.5135822296142578},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.48385679721832275},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33029186725616455},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15556129813194275},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2205.12493","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.12493","pdf_url":"https://arxiv.org/pdf/2205.12493","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2205.12493","doi":"https://doi.org/10.48550/arxiv.2205.12493","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2205.12493","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2205.12493","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.12493","pdf_url":"https://arxiv.org/pdf/2205.12493","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4408100315","https://openalex.org/W4229027123","https://openalex.org/W3202747382","https://openalex.org/W4387870920","https://openalex.org/W4377944278","https://openalex.org/W7129046988","https://openalex.org/W3203671050","https://openalex.org/W4361019765","https://openalex.org/W7125234843","https://openalex.org/W6943975934"],"abstract_inverted_index":{"Federated":[0,76],"Learning":[1],"has":[2],"become":[3],"an":[4],"important":[5],"learning":[6,82,94,128],"paradigm":[7],"due":[8],"to":[9,25,59,115],"its":[10,120],"privacy":[11],"and":[12,44,71,124,150,157,181,203],"computational":[13],"benefits.":[14],"As":[15,169],"the":[16,35,97,126,133,154,158,174,194,212,215],"field":[17],"advances,":[18],"two":[19],"key":[20,110],"challenges":[21,62],"that":[22,207],"still":[23],"remain":[24],"be":[26,146,183],"addressed":[27],"are:":[28],"(1)":[29],"system":[30],"heterogeneity":[31],"-":[32],"variability":[33],"in":[34,50,112,170,200],"compute":[36],"and/or":[37],"data":[38,49],"resources":[39],"present":[40],"on":[41,85,137],"each":[42,117],"client,":[43],"(2)":[45],"lack":[46],"of":[47,106,165,193,214],"labeled":[48,107,167],"certain":[51],"federated":[52],"settings.":[53],"Several":[54],"recent":[55],"developments":[56],"have":[57],"tried":[58],"overcome":[60],"these":[61],"independently.":[63],"In":[64],"this":[65],"work,":[66],"we":[67],"propose":[68],"a":[69,138,190,219],"unified":[70],"systematic":[72],"framework,":[73],"\\emph{Heterogeneous":[74],"Self-supervised":[75],"Learning}":[77],"(Hetero-SSFL)":[78],"for":[79,185,197],"enabling":[80],"self-supervised":[81,122,172],"with":[83],"federation":[84],"heterogeneous":[86,201],"clients.":[87],"The":[88,109,141],"proposed":[89,195,209],"framework":[90,196],"allows":[91],"collaborative":[92],"representation":[93],"across":[95,129],"all":[96],"clients":[98,130],"without":[99],"imposing":[100],"architectural":[101],"constraints":[102],"or":[103],"requiring":[104],"presence":[105,164],"data.":[108,168],"idea":[111],"Hetero-SSFL":[113],"is":[114],"let":[116],"client":[118,176],"train":[119],"unique":[121],"model":[123],"enable":[125],"joint":[127],"by":[131,218],"aligning":[132],"lower":[134],"dimensional":[135],"representations":[136],"common":[139],"dataset.":[140],"entire":[142],"training":[143,156],"procedure":[144],"could":[145],"viewed":[147],"as":[148,152],"self":[149],"peer-supervised":[151],"both":[153],"local":[155],"alignment":[159],"procedures":[160],"do":[161],"not":[162],"require":[163],"any":[166],"conventional":[171],"learning,":[173],"obtained":[175],"models":[177],"are":[178],"task":[179],"independent":[180],"can":[182],"used":[184],"varied":[186],"end-tasks.":[187],"We":[188],"provide":[189],"convergence":[191],"guarantee":[192],"non-convex":[198],"objectives":[199],"settings":[202],"also":[204],"empirically":[205],"demonstrate":[206],"our":[208],"approach":[210],"outperforms":[211],"state":[213],"art":[216],"methods":[217],"significant":[220],"margin.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2022-06-13T00:00:00"}