{"id":"https://openalex.org/W3130025260","doi":null,"title":"FedU: A Unified Framework for Federated Multi-Task Learning with Laplacian Regularization.","display_name":"FedU: A Unified Framework for Federated Multi-Task Learning with Laplacian Regularization.","publication_year":2021,"publication_date":"2021-02-14","ids":{"openalex":"https://openalex.org/W3130025260","mag":"3130025260"},"language":"en","primary_location":{"id":"mag:3130025260","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2102.07148","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://export.arxiv.org/pdf/2102.07148","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068465874","display_name":"Canh T. Dinh","orcid":"https://orcid.org/0000-0002-0205-7743","observed_orcids":["https://orcid.org/0000-0002-0205-7743"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Canh T. Dinh","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-0205-7743","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038151851","display_name":"Tung T. Vu","orcid":"https://orcid.org/0000-0002-8342-4567","observed_orcids":["https://orcid.org/0000-0002-8342-4567"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tung T. Vu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-8342-4567","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027558961","display_name":"Nguyen Hoang Khoi Tran","orcid":"https://orcid.org/0000-0001-7323-9213","observed_orcids":["https://orcid.org/0000-0001-7323-9213"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen H. Tran","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-7323-9213","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080867745","display_name":"Minh Ngoc Dao","orcid":"https://orcid.org/0000-0002-8074-6675","observed_orcids":["https://orcid.org/0000-0002-8074-6675"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minh N. Dao","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-8074-6675","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100412598","display_name":"Hongyu Zhang","orcid":"https://orcid.org/0000-0002-3063-9425","observed_orcids":["https://orcid.org/0000-0002-3063-9425","https://orcid.org/0000-0002-8333-9231","https://orcid.org/0009-0000-4303-441X","https://orcid.org/0009-0000-2889-4585","https://orcid.org/0009-0001-9871-126X","https://orcid.org/0009-0009-6332-4452"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongyu Zhang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-3063-9425","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":39,"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":0.9984999895095825,"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":0.9984999895095825,"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":0.00039999998989515007,"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/laplacian-regularization","display_name":"Laplacian regularization","score":0.9980000257492065},{"id":"https://openalex.org/keywords/personalized-federated-learning","display_name":"personalized federated learning","score":0.8500000238418579},{"id":"https://openalex.org/keywords/few-shot-learning","display_name":"few-shot learning","score":0.8740000128746033},{"id":"https://openalex.org/keywords/decentralized-federated-learning","display_name":"decentralized federated learning","score":0.8450000286102295},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.824999988079071},{"id":"https://openalex.org/keywords/nonconvex-optimization","display_name":"non-convex optimization","score":0.8019999861717224},{"id":"https://openalex.org/keywords/strongly-convex-optimization","display_name":"strongly convex optimization","score":0.5879999995231628},{"id":"https://openalex.org/keywords/customer-relationships","display_name":"customer relationships","score":0.4740000069141388}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8345056772232056},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7745608687400818},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7479158043861389},{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.6861147880554199},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.629684329032898},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.47484710812568665},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39780452847480774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38081854581832886},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3508513569831848},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3396693170070648},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14064311981201172},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.11877650022506714},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3130025260","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2102.07148","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3130025260","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2102.07148","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W134960717","https://openalex.org/W1942758450","https://openalex.org/W2018096278","https://openalex.org/W2112796928","https://openalex.org/W2130903752","https://openalex.org/W2143104527","https://openalex.org/W2157017541","https://openalex.org/W2236749180","https://openalex.org/W2541884796","https://openalex.org/W2783522756","https://openalex.org/W2794363191","https://openalex.org/W2795900505","https://openalex.org/W2804057271","https://openalex.org/W2804884917","https://openalex.org/W2804978897","https://openalex.org/W2807006176","https://openalex.org/W2900182564","https://openalex.org/W2913250055","https://openalex.org/W2913340405","https://openalex.org/W2914328083","https://openalex.org/W2958992393","https://openalex.org/W2963024938","https://openalex.org/W2963049866","https://openalex.org/W2963300197","https://openalex.org/W2963663068","https://openalex.org/W2964121793","https://openalex.org/W2970971581","https://openalex.org/W2976335444","https://openalex.org/W2980216952","https://openalex.org/W2982654255","https://openalex.org/W2990789643","https://openalex.org/W2995022099","https://openalex.org/W2995653155","https://openalex.org/W2996974038","https://openalex.org/W3003261073","https://openalex.org/W3005776401","https://openalex.org/W3006555759","https://openalex.org/W3007345209","https://openalex.org/W3012501605","https://openalex.org/W3012968339","https://openalex.org/W3034942609","https://openalex.org/W3035302051","https://openalex.org/W3035668299","https://openalex.org/W3037674069","https://openalex.org/W3037736379","https://openalex.org/W3097060730","https://openalex.org/W3099912322","https://openalex.org/W3100393648","https://openalex.org/W3100779497","https://openalex.org/W3118608800","https://openalex.org/W3145959995"],"related_works":["https://openalex.org/W4206878041","https://openalex.org/W3194794012","https://openalex.org/W7129570382","https://openalex.org/W3035668299","https://openalex.org/W4408124960","https://openalex.org/W4414856338","https://openalex.org/W2618494520","https://openalex.org/W4367724719","https://openalex.org/W7127348804","https://openalex.org/W4308867702"],"abstract_inverted_index":{"Federated":[0],"multi-task":[1,49],"learning":[2],"(FMTL)":[3],"has":[4],"emerged":[5],"as":[6,67,164,166],"a":[7,32,57,61],"natural":[8],"choice":[9],"to":[10,90,129,151],"capture":[11],"the":[12,16,23,46,100,123,137,160],"statistical":[13,28],"diversity":[14],"among":[15,45],"clients":[17,47],"in":[18,170],"federated":[19,69,72,172],"learning.":[20,50,79,173],"To":[21],"unleash":[22],"potential":[24],"of":[25,64,94,103,116,125],"FMTL":[26,34,139],"beyond":[27],"diversity,":[29],"we":[30,97,155],"formulate":[31],"new":[33],"problem":[35],"FedU":[36,55,126,158],"using":[37],"Laplacian":[38],"regularization,":[39],"which":[40,142],"can":[41],"explicitly":[42],"leverage":[43],"relationships":[44],"for":[48,110,119],"We":[51,80],"first":[52],"show":[53,98],"that":[54,99,157],"provides":[56],"unified":[58],"framework":[59],"covering":[60],"wide":[62],"range":[63],"problems":[65],"such":[66],"conventional":[68,138],"learning,":[70,73,75],"personalized":[71,171],"few-shot":[74],"and":[76,87,113,133,168],"stratified":[77],"model":[78],"then":[81],"propose":[82],"algorithms":[83,106],"including":[84],"both":[85,104,130],"communication-centralized":[86],"decentralized":[88],"schemes":[89],"learn":[91],"optimal":[92],"models":[93],"FedU.":[95],"Theoretically,":[96],"convergence":[101],"rates":[102],"FedU's":[105],"achieve":[107],"linear":[108],"speedup":[109,115],"strongly":[111,131],"convex":[112,132,152],"sublinear":[114],"order":[117],"$1/2$":[118],"nonconvex":[120,134],"objectives.":[121],"While":[122],"analysis":[124],"is":[127,143,148],"applicable":[128,150],"loss":[135],"functions,":[136],"algorithm":[140],"MOCHA,":[141,163],"based":[144],"on":[145],"CoCoA":[146],"framework,":[147],"only":[149],"case.":[153],"Experimentally,":[154],"verify":[156],"outperforms":[159],"vanilla":[161],"FedAvg,":[162],"well":[165],"pFedMe":[167],"Per-FedAvg":[169]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":11}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2021-03-01T00:00:00"}