{"id":"https://openalex.org/W4224254202","doi":"https://doi.org/10.48550/arxiv.2204.09715","title":"Scaling Language Model Size in Cross-Device Federated Learning","display_name":"Scaling Language Model Size in Cross-Device Federated Learning","publication_year":2022,"publication_date":"2022-03-31","ids":{"openalex":"https://openalex.org/W4224254202","doi":"https://doi.org/10.48550/arxiv.2204.09715"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2204.09715","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.09715","pdf_url":"https://arxiv.org/pdf/2204.09715","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2204.09715","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075278288","display_name":"Jae Hun Ro","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ro, Jae Hun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063381559","display_name":"Theresa Breiner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Breiner, Theresa","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068382750","display_name":"Lara McConnaughey","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"McConnaughey, Lara","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101957763","display_name":"Mingqing Chen","orcid":"https://orcid.org/0000-0002-6430-7576"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Mingqing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103890688","display_name":"Ananda Theertha Suresh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suresh, Ananda Theertha","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101780732","display_name":"Shankar Kumar","orcid":"https://orcid.org/0009-0001-4307-8102"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kumar, Shankar","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5075324202","display_name":"Rajiv Mathews","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mathews, Rajiv","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5075278288"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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":0.9995999932289124,"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":0.9995999932289124,"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":0.9848999977111816,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.965399980545044,"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/perplexity","display_name":"Perplexity","score":0.9889283180236816},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7925865650177002},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7044894099235535},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6319716572761536},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6274056434631348},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.601205587387085},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5765750408172607},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5661527514457703},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.46335840225219727},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4603080749511719},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.428469717502594},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36145302653312683},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14671647548675537}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9889283180236816},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7925865650177002},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7044894099235535},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6319716572761536},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6274056434631348},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.601205587387085},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5765750408172607},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5661527514457703},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.46335840225219727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4603080749511719},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.428469717502594},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36145302653312683},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14671647548675537},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2204.09715","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.09715","pdf_url":"https://arxiv.org/pdf/2204.09715","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2204.09715","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2204.09715","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2204.09715","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.09715","pdf_url":"https://arxiv.org/pdf/2204.09715","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4287323699","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2787311093","https://openalex.org/W2084531783","https://openalex.org/W2902731467"],"abstract_inverted_index":{"Most":[0],"studies":[1],"in":[2,35,95],"cross-device":[3,36],"federated":[4,37],"learning":[5],"focus":[6],"on":[7],"small":[8],"models,":[9],"due":[10],"to":[11,30,56],"the":[12,68],"server-client":[13],"communication":[14,84],"and":[15,50,62,86],"on-device":[16],"computation":[17],"bottlenecks.":[18],"In":[19],"this":[20],"work,":[21],"we":[22,53],"leverage":[23],"various":[24],"techniques":[25],"for":[26],"mitigating":[27],"these":[28],"bottlenecks":[29],"train":[31,57],"larger":[32],"language":[33],"models":[34],"learning.":[38],"With":[39],"systematic":[40],"applications":[41],"of":[42,75],"partial":[43],"model":[44],"training,":[45],"quantization,":[46],"efficient":[47],"transfer":[48],"learning,":[49],"communication-efficient":[51],"optimizers,":[52],"are":[54],"able":[55],"a":[58,76],"$21$M":[59],"parameter":[60,64],"Transformer":[61],"$20.2$M":[63],"Conformer":[65],"that":[66,74],"achieve":[67],"same":[69],"or":[70],"better":[71],"perplexity":[72,89],"as":[73],"similarly":[77],"sized":[78],"LSTM":[79],"with":[80],"$\\sim10\\times$":[81],"smaller":[82,91],"client-to-server":[83],"cost":[85],"$11\\%$":[87],"lower":[88],"than":[90],"LSTMs":[92],"commonly":[93],"studied":[94],"literature.":[96]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}