{"id":"https://openalex.org/W7118972840","doi":"https://doi.org/10.48550/arxiv.2601.00853","title":"FedSCAM (Federated Sharpness-Aware Minimization with Clustered Aggregation and Modulation): Scam-resistant SAM for Robust Federated Optimization in Heterogeneous Environments","display_name":"FedSCAM (Federated Sharpness-Aware Minimization with Clustered Aggregation and Modulation): Scam-resistant SAM for Robust Federated Optimization in Heterogeneous Environments","publication_year":2025,"publication_date":"2025-12-29","ids":{"openalex":"https://openalex.org/W7118972840","doi":"https://doi.org/10.48550/arxiv.2601.00853"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2601.00853","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.00853","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"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":"https://doi.org/10.48550/arxiv.2601.00853","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122051671","display_name":"Sameer Rahil","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Rahil, Sameer","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122137289","display_name":"Zain Abdullah Ahmad","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmad, Zain Abdullah","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5122147021","display_name":"Talha Asif","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Asif, Talha","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5122051671"],"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":0.8120999932289124,"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":0.8120999932289124,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0617000013589859,"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":0.02160000056028366,"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/skew","display_name":"Skew","score":0.7649999856948853},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.755299985408783},{"id":"https://openalex.org/keywords/perturbation","display_name":"Perturbation (astronomy)","score":0.5694000124931335},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4884999990463257},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4171000123023987},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.41179999709129333},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4052000045776367},{"id":"https://openalex.org/keywords/global-optimization","display_name":"Global optimization","score":0.382099986076355}],"concepts":[{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.7649999856948853},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.755299985408783},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7116000056266785},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.5694000124931335},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4884999990463257},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4837999939918518},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4171000123023987},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.41179999709129333},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4052000045776367},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4018999934196472},{"id":"https://openalex.org/C164752517","wikidata":"https://www.wikidata.org/wiki/Q5570875","display_name":"Global optimization","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3499000072479248},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.3393999934196472},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C2987595161","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Optimization algorithm","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C89109886","wikidata":"https://www.wikidata.org/wiki/Q1535924","display_name":"Trust region","level":3,"score":0.29919999837875366},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29739999771118164},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C107321475","wikidata":"https://www.wikidata.org/wiki/Q5374254","display_name":"Empirical risk minimization","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.2612000107765198}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2601.00853","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.00853","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2601.00853","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.00853","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":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":[7,56],"decentralized":[8],"edge":[9],"devices":[10],"while":[11],"preserving":[12],"data":[13],"privacy.":[14],"However,":[15],"statistical":[16],"heterogeneity":[17,92,97],"among":[18,161],"clients,":[19,58],"often":[20],"manifested":[21],"as":[22],"non-IID":[23],"label":[24,153],"distributions,":[25],"poses":[26],"significant":[27],"challenges":[28],"to":[29,40,42,108],"convergence":[30,171],"and":[31,74,86,102,146,173],"generalization.":[32],"While":[33],"Sharpness-Aware":[34,69],"Minimization":[35,70],"(SAM)":[36],"has":[37],"been":[38],"introduced":[39],"FL":[41],"seek":[43],"flatter,":[44],"more":[45],"robust":[46],"minima,":[47],"existing":[48],"approaches":[49],"typically":[50],"apply":[51],"a":[52,76,96,125],"uniform":[53],"perturbation":[54,84,105],"radius":[55,85,106],"all":[57],"ignoring":[59],"client-specific":[60,91],"heterogeneity.":[61],"In":[62],"this":[63,109],"work,":[64],"we":[65,123],"propose":[66],"\\textbf{FedSCAM}":[67],"(Federated":[68],"with":[71,114,137],"Clustered":[72],"Aggregation":[73],"Modulation),":[75],"novel":[77],"algorithm":[78],"that":[79,130,135,156],"dynamically":[80],"adjusts":[81],"the":[82,104,119,138],"SAM":[83],"aggregation":[87,128],"weights":[88],"based":[89],"on":[90,144],"scores.":[93],"By":[94],"calculating":[95],"metric":[98],"for":[99],"each":[100],"client":[101],"modulating":[103],"inversely":[107],"score,":[110],"FedSCAM":[111,157],"prevents":[112],"clients":[113,134],"high":[115],"variance":[116],"from":[117,133],"destabilizing":[118],"global":[120,139],"model.":[121],"Furthermore,":[122],"introduce":[124],"heterogeneity-aware":[126],"weighted":[127],"mechanism":[129],"prioritizes":[131],"updates":[132],"align":[136],"optimization":[140],"direction.":[141],"Extensive":[142],"experiments":[143],"CIFAR-10":[145],"Fashion-MNIST":[147],"under":[148],"various":[149],"degrees":[150],"of":[151,170],"Dirichlet-based":[152],"skew":[154],"demonstrate":[155],"achieves":[158],"competitive":[159],"performance":[160],"state-of-the-art":[162],"baselines,":[163],"including":[164],"FedSAM,":[165],"FedLESAM,":[166],"etc.":[167],"in":[168],"terms":[169],"speed":[172],"final":[174],"test":[175],"accuracy.":[176]},"counts_by_year":[],"updated_date":"2026-01-08T20:10:11.968330","created_date":"2026-01-08T00:00:00"}