{"id":"https://openalex.org/W7117153556","doi":"https://doi.org/10.48550/arxiv.2512.17986","title":"FedOAED: Federated On-Device Autoencoder Denoiser for Heterogeneous Data under Limited Client Availability","display_name":"FedOAED: Federated On-Device Autoencoder Denoiser for Heterogeneous Data under Limited Client Availability","publication_year":2025,"publication_date":"2025-12-19","ids":{"openalex":"https://openalex.org/W7117153556","doi":"https://doi.org/10.48550/arxiv.2512.17986"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2512.17986","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.17986","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.2512.17986","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121183337","display_name":"S M Ruhul Kabir Howlader","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Howlader, S M Ruhul Kabir","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121238158","display_name":"Xiao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121126186","display_name":"Yifei Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Yifei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5121150146","display_name":"Lu Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Lu","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":0.7458999752998352,"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":0.7458999752998352,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.027000000700354576,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.02319999970495701,"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/autoencoder","display_name":"Autoencoder","score":0.8820000290870667},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.6845999956130981},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.6693999767303467},{"id":"https://openalex.org/keywords/health-insurance-portability-and-accountability-act","display_name":"Health Insurance Portability and Accountability Act","score":0.47839999198913574},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.47110000252723694},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.44929999113082886},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.32919999957084656}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8820000290870667},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7839000225067139},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.6845999956130981},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6693999767303467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5282999873161316},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4860999882221222},{"id":"https://openalex.org/C2778306010","wikidata":"https://www.wikidata.org/wiki/Q606563","display_name":"Health Insurance Portability and Accountability Act","level":3,"score":0.47839999198913574},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.47110000252723694},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.44929999113082886},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36660000681877136},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.26820001006126404},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2639000117778778},{"id":"https://openalex.org/C2776007630","wikidata":"https://www.wikidata.org/wiki/Q2798912","display_name":"Accountability","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2512.17986","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.17986","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.2512.17986","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.17986","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":0.6087228059768677}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Over":[0],"the":[1,33,40,121,135],"last":[2],"few":[3],"decades,":[4],"machine":[5],"learning":[6,10,108],"(ML)":[7],"and":[8,39,44,92,120,141],"deep":[9],"(DL)":[11],"solutions":[12],"have":[13,48],"demonstrated":[14],"their":[15],"potential":[16],"across":[17],"many":[18,50],"applications":[19,52],"by":[20,124],"leveraging":[21],"large":[22],"amounts":[23],"of":[24],"high-quality":[25],"data.":[26],"However,":[27],"strict":[28],"data-sharing":[29],"regulations":[30],"such":[31],"as":[32],"General":[34],"Data":[35],"Protection":[36],"Regulation":[37],"(GDPR)":[38],"Health":[41],"Insurance":[42],"Portability":[43],"Accountability":[45],"Act":[46],"(HIPAA)":[47],"prevented":[49],"data-driven":[51],"from":[53,95,115,144],"being":[54],"realised.":[55],"Federated":[56],"Learning":[57],"(FL),":[58],"in":[59,70,79],"which":[60,87],"raw":[61],"data":[62,146],"never":[63],"leaves":[64],"local":[65,117],"devices,":[66],"has":[67,76],"shown":[68],"promise":[69],"overcoming":[71],"these":[72],"limitations.":[73],"Although":[74],"FL":[75],"grown":[77],"rapidly":[78],"recent":[80],"years,":[81],"it":[82],"still":[83],"struggles":[84],"with":[85],"heterogeneity,":[86],"produces":[88],"gradient":[89],"noise,":[90],"client-drift,":[91],"increased":[93],"variance":[94,122,142],"partial":[96,125],"client":[97,126,136,149],"participation.":[98,127],"In":[99],"this":[100],"paper,":[101],"we":[102],"propose":[103],"FedOAED,":[104],"a":[105],"novel":[106],"federated":[107],"algorithm":[109],"designed":[110],"to":[111,138],"mitigate":[112,139],"client-drift":[113,140],"arising":[114],"multiple":[116,153],"training":[118],"updates":[119],"induced":[123],"FedOAED":[128,161],"incorporates":[129],"an":[130],"on-device":[131],"autoencoder":[132],"denoiser":[133],"on":[134,152],"side":[137],"resulting":[143],"heterogeneous":[145],"under":[147,156],"limited":[148],"availability.":[150],"Experiments":[151],"vision":[154],"datasets":[155],"Non-IID":[157],"settings":[158],"demonstrate":[159],"that":[160],"consistently":[162],"outperforms":[163],"state-of-the-art":[164],"baselines.":[165]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-12-24T00:00:00"}