{"id":"https://openalex.org/W7164877851","doi":"https://doi.org/10.48550/arxiv.2606.15963","title":"PreLort: Prefix-Nested LoRA for Federated Fine-Tuning under Rank Heterogeneity","display_name":"PreLort: Prefix-Nested LoRA for Federated Fine-Tuning under Rank Heterogeneity","publication_year":2026,"publication_date":"2026-06-14","ids":{"openalex":"https://openalex.org/W7164877851","doi":"https://doi.org/10.48550/arxiv.2606.15963"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.15963","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15963","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2606.15963","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013537370","display_name":"Muhammad Waseem","orcid":"https://orcid.org/0000-0001-7488-2577"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Waseem, Muhammad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138714836","display_name":"Nurbek Tastan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tastan, Nurbek","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138704742","display_name":"Andrej Jovanovic","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jovanovic, Andrej","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138706260","display_name":"Nicholas D. Lane","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lane, Nicholas D.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086633938","display_name":"Nils Lukas","orcid":"https://orcid.org/0009-0001-5891-9154"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lukas, Nils","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059676452","display_name":"Karthik Nandakumar","orcid":"https://orcid.org/0000-0002-6274-9725"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nandakumar, Karthik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138732652","display_name":"Samuel Horvath","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Horvath, Samuel","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":0.25110000371932983,"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":0.25110000371932983,"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/T14347","display_name":"Big Data and Digital Economy","score":0.08579999953508377,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.08209999650716782,"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/prefix","display_name":"Prefix","score":0.7986999750137329},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.7123000025749207},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5418999791145325},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5008000135421753},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.38580000400543213},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.3727000057697296},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.3671000003814697},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.33869999647140503}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.805899977684021},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.7986999750137329},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.7123000025749207},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5418999791145325},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5008000135421753},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.38580000400543213},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38519999384880066},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.3727000057697296},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.349700003862381},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3197000026702881},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.3176000118255615},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.301800012588501},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2818000018596649},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26100000739097595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2563000023365021},{"id":"https://openalex.org/C82578977","wikidata":"https://www.wikidata.org/wiki/Q16773055","display_name":"Data aggregator","level":3,"score":0.2522999942302704},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.15963","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15963","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.15963","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15963","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.413697212934494,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Federated":[0],"fine-tuning":[1],"of":[2,15,56],"large":[3],"language":[4],"models":[5],"using":[6],"parameter-efficient":[7],"methods":[8,35,194],"such":[9],"as":[10,23,175],"LoRA":[11,70,193],"enables":[12],"privacy-preserving":[13],"adaptation":[14],"foundation":[16],"models.":[17,208],"Heterogeneous":[18],"hardware":[19],"resources":[20],"introduce":[21,98],"challenges,":[22],"clients":[24,108,165],"with":[25],"different":[26],"adapter":[27,73,129],"ranks":[28],"cannot":[29],"be":[30],"directly":[31],"aggregated.":[32,182],"While":[33],"existing":[34],"enable":[36],"aggregation":[37,102],"under":[38,130],"heterogeneous":[39,191],"ranks,":[40],"they":[41],"fail":[42],"to":[43,53,110,137,166],"control":[44],"how":[45],"information":[46,170],"is":[47],"distributed":[48],"across":[49,205],"rank":[50,112,132],"dimensions,":[51],"leading":[52],"suboptimal":[54],"use":[55],"shared":[57],"low-rank":[58,66,140,149,164],"representations.":[59],"Instead,":[60],"we":[61,97],"propose":[62],"PreLort:":[63],"a":[64,76,100,122,147],"nested":[65],"formulation":[67],"for":[68],"federated":[69,192],"that":[71,82,104,126,185],"organizes":[72],"dimensions":[74,84,90,158,177],"into":[75],"prefix":[77,141,150,176],"hierarchy.":[78],"Our":[79],"approach":[80],"ensures":[81],"lower-rank":[83,118],"encode":[85],"task-relevant":[86,154],"information,":[87,155],"while":[88,156,199],"higher-rank":[89,157,173],"capture":[91],"additional":[92,160],"capacity.":[93,161],"Building":[94],"on":[95],"this,":[96],"(i)":[99],"segment-wise":[101],"rule":[103],"averages":[105],"only":[106],"over":[107],"contributing":[109],"each":[111,128],"segment,":[113],"avoiding":[114],"dilution":[115],"from":[116,168],"zero-padded":[117],"clients,":[119,174],"and":[120,181,197],"(ii)":[121],"prefix-nested":[123],"training":[124],"strategy":[125],"optimizes":[127],"multiple":[131,206],"truncations,":[133],"encouraging":[134],"useful":[135],"signal":[136],"concentrate":[138],"in":[139,195],"dimensions.":[142],"Together,":[143],"these":[144],"components":[145],"encourage":[146],"consistent":[148],"capturing":[151],"the":[152],"most":[153],"learn":[159],"This":[162],"allows":[163],"benefit":[167],"richer":[169],"contributed":[171],"by":[172],"are":[178],"consistently":[179,188],"learned":[180],"Experiments":[183],"demonstrate":[184],"our":[186],"method":[187],"outperforms":[189],"prior":[190],"accuracy":[196],"ROUGE-L,":[198],"achieving":[200],"lower":[201],"or":[202],"comparable":[203],"perplexity":[204],"base":[207]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-17T00:00:00"}