{"id":"https://openalex.org/W7154232145","doi":"https://doi.org/10.1201/9781998511273-11","title":"FedNLP: Secure and Efficient Federated Learning Using NLP (Architecture, Challenges, and Solutions)","display_name":"FedNLP: Secure and Efficient Federated Learning Using NLP (Architecture, Challenges, and Solutions)","publication_year":2026,"publication_date":"2026-04-14","ids":{"openalex":"https://openalex.org/W7154232145","doi":"https://doi.org/10.1201/9781998511273-11"},"language":"en","primary_location":{"id":"doi:10.1201/9781998511273-11","doi":"https://doi.org/10.1201/9781998511273-11","is_oa":false,"landing_page_url":"https://doi.org/10.1201/9781998511273-11","pdf_url":null,"source":{"id":"https://openalex.org/S4306462842","display_name":"Apple Academic Press eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Processing and Artificial Intelligence","raw_type":"book-chapter"},"volume":{"id":"https://openalex.org/W7154379608","display_name":"Natural Language Processing and Artificial Intelligence"},"type":"book-chapter","is_traditional":true,"indexed_in":["crossref"],"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/A5107288423","display_name":"Ekta Bhaggi","orcid":"https://orcid.org/0009-0004-7347-9822","observed_orcids":["https://orcid.org/0009-0004-7347-9822"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ekta Bhaggi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125907713","display_name":"Varsha","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Varsha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133610324","display_name":"Komal","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Komal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133599560","display_name":"Mamta Devi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mamta Devi","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"269","last_page":"299"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":1.0,"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":1.0,"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":0.0,"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":0.0,"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":0.9679999947547913},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"natural language processing","score":0.9049999713897705},{"id":"https://openalex.org/keywords/privacy-protection","display_name":"privacy preservation","score":0.5230000019073486},{"id":"https://openalex.org/keywords/edge-devices","display_name":"edge devices","score":0.6690000295639038},{"id":"https://openalex.org/keywords/training-efficiency","display_name":"training efficiency","score":0.6069999933242798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8406999707221985},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.8199999928474426},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.75},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.6331999897956848},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.579200029373169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5281000137329102},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.4090999960899353},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.4016000032424927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3993000090122223},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C99221444","wikidata":"https://www.wikidata.org/wiki/Q1532069","display_name":"Private information retrieval","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2750000059604645},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C2992317946","wikidata":"https://www.wikidata.org/wiki/Q712144","display_name":"De facto","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1201/9781998511273-11","doi":"https://doi.org/10.1201/9781998511273-11","is_oa":false,"landing_page_url":"https://doi.org/10.1201/9781998511273-11","pdf_url":null,"source":{"id":"https://openalex.org/S4306462842","display_name":"Apple Academic Press eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Processing and Artificial Intelligence","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4281382076","https://openalex.org/W4387212306","https://openalex.org/W4387007373","https://openalex.org/W3153137927","https://openalex.org/W4287207694","https://openalex.org/W3212066318","https://openalex.org/W3183712004","https://openalex.org/W4415713028","https://openalex.org/W4403343568","https://openalex.org/W7163892458"],"abstract_inverted_index":{"The":[0,87,106,238],"use":[1,141,295],"of":[2,109,121,142,146,164,299,311],"federated":[3,288,300,315],"learning":[4,25,50,172,191,289],"(FL),":[5],"which":[6,43,63,96,179],"prioritizes":[7],"privacy":[8,163,218,304],"protection,":[9],"has":[10,34,260],"grown":[11],"significantly":[12,114],"in":[13,178,203,230,245,314],"recent":[14],"years.":[15],"FL":[16,139,248],"is":[17,51,132,158,173,210],"now":[18],"a":[19,36,152,174,187,213,246],"well-known":[20],"paradigm":[21],"for":[22,56,60,91],"training":[23,116,129,233],"machine":[24],"(ML)":[26],"systems":[27,207],"that":[28,73,257],"span":[29],"distributed,":[30],"large-scale":[31],"contexts.":[32],"NLP":[33],"undergone":[35],"revolution":[37],"thanks":[38],"to":[39,124,150,185,195,205,212,274,294],"transformer-based":[40],"pre-trained":[41,58],"models,":[42],"offer":[44],"better":[45],"performance":[46],"and":[47,78,112,118,219,252,302,306],"generality.":[48],"Federated":[49,171,190],"the":[52,74,128,133,143,162,165,193,196,231,254,297,312],"de":[53],"facto":[54],"method":[55],"fine-tuning":[57],"models":[59,256],"downstream":[61],"tasks,":[62],"frequently":[64],"require":[65],"private":[66,265],"data":[67,123,167,197,209,217],"(FedNLP).":[68],"Nevertheless,":[69],"our":[70],"observations":[71],"reveal":[72],"massive":[75],"model":[76,104,154,194],"sizes":[77],"associated":[79],"high":[80],"network/computation":[81],"costs":[82],"make":[83],"FedNLP":[84,93],"unreasonably":[85],"slow.":[86],"main":[88],"building":[89],"blocks":[90],"practical":[92],"are":[94,97,221,279],"adapters,":[95],"modest":[98],"bottleneck":[99],"modules":[100],"introduced":[101],"at":[102,127],"different":[103],"layers.":[105],"correct":[107],"configuration":[108],"adapter":[110],"depth":[111],"width":[113],"affects":[115],"efficiency":[117],"speed.":[119],"Instead":[120],"requiring":[122],"be":[125],"centralized":[126],"location,":[130],"as":[131,223,242],"case":[134],"with":[135,309],"traditional":[136],"ML":[137,276],"techniques,":[138,277],"makes":[140],"computational":[144],"power":[145],"several":[147,180],"edge":[148],"devices":[149,200],"train":[151,186],"global":[153],"jointly.":[155],"Importantly,":[156],"this":[157,271],"done":[159],"while":[160],"maintaining":[161],"local":[166,236,255],"on":[168,198],"each":[169,224,258],"device.":[170],"distributed":[175],"machine-learning":[176],"technique":[177],"computers":[181],"or":[182,201,226],"servers":[183],"cooperate":[184],"single":[188],"model.":[189],"delivers":[192],"individual":[199],"servers,":[202],"contrast":[204],"conventional":[206,275],"where":[208],"routed":[211],"central":[214,239],"server.":[215],"Thus,":[216],"security":[220],"guaranteed":[222],"device":[225],"server":[227,240],"can":[228],"participate":[229],"model\u2019s":[232],"using":[234,262],"its":[235,291],"data.":[237],"acts":[241],"an":[243],"orchestrator":[244],"typical":[247],"arrangement.":[249],"It":[250],"gathers":[251],"combines":[253],"client":[259],"trained":[261],"their":[263],"unique":[264],"data,":[266],"iteratively":[267],"until":[268],"completion.":[269],"Comparing":[270],"decentralized":[272],"approach":[273],"there":[278],"many":[280],"benefits.":[281],"This":[282],"chapter":[283],"provides":[284],"information":[285],"about":[286],"what":[287],"is,":[290],"types,":[292],"why":[293],"it,":[296],"working":[298],"learning,":[301],"some":[303,310],"challenges":[305],"issues":[307],"along":[308],"solutions":[313],"learning.":[316]},"counts_by_year":[],"updated_date":"2026-10-10T09:11:00.788812","created_date":"2026-04-15T00:00:00"}