{"id":"https://openalex.org/W7167222317","doi":"https://doi.org/10.48550/arxiv.2607.02447","title":"Understanding the Robustness of Distributed Self-Supervised Learning Frameworks Against Non-IID Data","display_name":"Understanding the Robustness of Distributed Self-Supervised Learning Frameworks Against Non-IID Data","publication_year":2026,"publication_date":"2026-07-02","ids":{"openalex":"https://openalex.org/W7167222317","doi":"https://doi.org/10.48550/arxiv.2607.02447"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.02447","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.02447","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.2607.02447","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139957059","display_name":"Xuanyu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xuanyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139955907","display_name":"Nan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Nan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139980013","display_name":"Shuai Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Shuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139977276","display_name":"Dong Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Dong","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":0.48539999127388,"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":0.48539999127388,"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":0.24650000035762787,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.025200000032782555,"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/robustness","display_name":"Robustness (evolution)","score":0.814300000667572},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7146999835968018},{"id":"https://openalex.org/keywords/distributed-learning","display_name":"Distributed learning","score":0.46810001134872437},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.4569999873638153},{"id":"https://openalex.org/keywords/independent-and-identically-distributed-random-variables","display_name":"Independent and identically distributed random variables","score":0.40540000796318054},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.37310001254081726}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.814300000667572},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7404999732971191},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7146999835968018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.490200012922287},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.46810001134872437},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.4569999873638153},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4339999854564667},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42899999022483826},{"id":"https://openalex.org/C141513077","wikidata":"https://www.wikidata.org/wiki/Q378542","display_name":"Independent and identically distributed random variables","level":3,"score":0.40540000796318054},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3440999984741211},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27639999985694885}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.02447","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.02447","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.2607.02447","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.02447","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"research":[1],"has":[2],"introduced":[3],"distributed":[4,154],"self-supervised":[5],"learning":[6,100,108],"(D-SSL)":[7],"approaches":[8],"to":[9,38,78],"leverage":[10],"vast":[11],"amounts":[12],"of":[13,23,32,51,54,89,121,131,140,165,171],"unlabeled":[14],"decentralized":[15,90,107],"data.":[16],"However,":[17],"D-SSL":[18,35,55,123],"faces":[19],"the":[20,52,87,119,128,141,163],"critical":[21],"challenge":[22],"data":[24,80],"heterogeneity,":[25],"and":[26,60,85,153,160],"there":[27],"is":[28,74,102],"limited":[29],"theoretical":[30,49,115,158],"understanding":[31],"how":[33],"different":[34],"frameworks":[36,56],"respond":[37],"this":[39,43],"challenge.":[40],"To":[41,125],"fill":[42],"gap,":[44],"we":[45,134],"present":[46],"a":[47,113,138],"rigorous":[48],"analysis":[50],"robustness":[53,88],"under":[57],"non-IID":[58],"(non-independent":[59],"identically":[61],"distributed)":[62],"settings.":[63],"Our":[64],"results":[65],"show":[66],"that":[67,86,98],"pre-training":[68],"with":[69,93,144],"Masked":[70],"Image":[71],"Modeling":[72],"(MIM)":[73],"inherently":[75],"more":[76],"robust":[77,105],"heterogeneous":[79],"than":[81,106],"Contrastive":[82],"Learning":[83],"(CL),":[84],"SSL":[91],"increases":[92],"average":[94],"network":[95],"connectivity,":[96],"implying":[97],"federated":[99],"(FL)":[101],"no":[103],"less":[104],"(DecL).":[109],"These":[110],"findings":[111],"provide":[112],"solid":[114],"foundation":[116],"for":[117],"guiding":[118],"design":[120],"future":[122],"algorithms.":[124],"further":[126],"illustrate":[127],"practical":[129],"implications":[130],"our":[132,157,172],"theory,":[133],"introduce":[135],"MAR":[136,166],"loss,":[137],"refinement":[139],"MIM":[142],"objective":[143],"local-to-global":[145],"alignment":[146],"regularization.":[147],"Extensive":[148],"experiments":[149],"across":[150],"model":[151],"architectures":[152],"settings":[155],"validate":[156],"insights,":[159],"additionally":[161],"confirm":[162],"effectiveness":[164],"loss":[167],"as":[168],"an":[169],"application":[170],"analysis.":[173]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-04T00:00:00"}