{"id":"https://openalex.org/W7128681841","doi":"https://doi.org/10.48550/arxiv.2602.10595","title":"Roughness-Informed Federated Learning","display_name":"Roughness-Informed Federated Learning","publication_year":2026,"publication_date":"2026-02-11","ids":{"openalex":"https://openalex.org/W7128681841","doi":"https://doi.org/10.48550/arxiv.2602.10595"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.10595","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125763722","display_name":"Mohammad Partohaghighi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Partohaghighi, Mohammad","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005703929","display_name":"Roummel F. Marcia","orcid":"https://orcid.org/0000-0001-6838-140X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marcia, Roummel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125725320","display_name":"Bruce J. West","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"West, Bruce J.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100715957","display_name":"YangQuan Chen","orcid":"https://orcid.org/0000-0002-7422-5988"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, YangQuan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5125763722"],"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":0.8299000263214111,"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":0.8299000263214111,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.05079999938607216,"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":0.026100000366568565,"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":0.8115000128746033},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7099000215530396},{"id":"https://openalex.org/keywords/distributed-learning","display_name":"Distributed learning","score":0.6284000277519226},{"id":"https://openalex.org/keywords/independent-and-identically-distributed-random-variables","display_name":"Independent and identically distributed random variables","score":0.5519999861717224},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4925999939441681},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.478300005197525},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.37040001153945923}],"concepts":[{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.8115000128746033},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8004999756813049},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7099000215530396},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.6284000277519226},{"id":"https://openalex.org/C141513077","wikidata":"https://www.wikidata.org/wiki/Q378542","display_name":"Independent and identically distributed random variables","level":3,"score":0.5519999861717224},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5074999928474426},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4925999939441681},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.478300005197525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38920000195503235},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.37040001153945923},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36880001425743103},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3490000069141388},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.33469998836517334},{"id":"https://openalex.org/C138020889","wikidata":"https://www.wikidata.org/wiki/Q2349659","display_name":"Collaborative learning","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C189237950","wikidata":"https://www.wikidata.org/wiki/Q2500758","display_name":"Stationary point","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2612000107765198}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.10595","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.10595","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.10595","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:doi:10.48550/arxiv.2602.10595","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"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],"Learning":[1],"(FL)":[2],"enables":[3],"collaborative":[4],"model":[5],"training":[6],"across":[7],"distributed":[8,21],"clients":[9],"while":[10],"preserving":[11],"data":[12],"privacy,":[13],"yet":[14],"faces":[15],"challenges":[16],"in":[17,83,132,149],"non-independent":[18],"and":[19,111,124,129,144],"identically":[20],"(non-IID)":[22],"settings":[23],"due":[24],"to":[25,72,99,140],"client":[26,40],"drift,":[27],"which":[28],"impairs":[29],"convergence.":[30],"We":[31,86],"propose":[32],"RI-FedAvg,":[33,68],"a":[34,44,88,100],"novel":[35],"FL":[36],"algorithm":[37],"that":[38,96,114],"mitigates":[39],"drift":[41],"by":[42],"incorporating":[43],"Roughness":[45],"Index":[46],"(RI)-based":[47],"regularization":[48],"term":[49],"into":[50],"the":[51,59,70,74,142],"local":[52,62],"objective,":[53],"adaptively":[54],"penalizing":[55],"updates":[56],"based":[57],"on":[58,108],"fluctuations":[60],"of":[61,76,146],"loss":[63,78],"landscapes.":[64],"This":[65],"paper":[66],"introduces":[67],"leveraging":[69],"RI":[71],"quantify":[73],"roughness":[75],"high-dimensional":[77],"functions,":[79],"ensuring":[80],"robust":[81],"optimization":[82],"heterogeneous":[84,151],"settings.":[85],"provide":[87],"rigorous":[89],"convergence":[90,131],"analysis":[91],"for":[92],"non-convex":[93],"objectives,":[94],"establishing":[95],"RI-FedAvg":[97,115],"converges":[98],"stationary":[101],"point":[102],"under":[103],"standard":[104],"assumptions.":[105],"Extensive":[106],"experiments":[107],"MNIST,":[109],"CIFAR-10,":[110],"CIFAR-100":[112],"demonstrate":[113],"outperforms":[116],"state-of-the-art":[117],"baselines,":[118],"including":[119],"FedAvg,":[120],"FedProx,":[121],"FedDyn,":[122],"SCAFFOLD,":[123],"DP-FedAvg,":[125],"achieving":[126],"higher":[127],"accuracy":[128],"faster":[130],"non-IID":[133],"scenarios.":[134],"Our":[135],"results":[136],"highlight":[137],"RI-FedAvg's":[138],"potential":[139],"enhance":[141],"robustness":[143],"efficiency":[145],"federated":[147],"learning":[148],"practical,":[150],"environments.":[152]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-13T00:00:00"}