{"id":"https://openalex.org/W7161025091","doi":"https://doi.org/10.48550/arxiv.2605.11010","title":"A Comparative Study of Federated Learning Aggregation Strategies under Homogeneous and Heterogeneous Data Distributions","display_name":"A Comparative Study of Federated Learning Aggregation Strategies under Homogeneous and Heterogeneous Data Distributions","publication_year":2026,"publication_date":"2026-05-10","ids":{"openalex":"https://openalex.org/W7161025091","doi":"https://doi.org/10.48550/arxiv.2605.11010"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.11010","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11010","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":"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.2605.11010","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136060819","display_name":"Antonios Makris","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Makris, Antonios","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134885093","display_name":"Christos Dousis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dousis, Christos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025744557","display_name":"Emmanouil Kritharakis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kritharakis, Emmanouil","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136079141","display_name":"Stavros Bouras","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bouras, Stavros","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136087620","display_name":"Konstantinos Tserpes","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tserpes, Konstantinos","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":0.8682000041007996,"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":0.8682000041007996,"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":0.012000000104308128,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.008700000122189522,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7153000235557556},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.7093999981880188},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6201000213623047},{"id":"https://openalex.org/keywords/data-aggregator","display_name":"Data aggregator","score":0.5368000268936157},{"id":"https://openalex.org/keywords/transformative-learning","display_name":"Transformative learning","score":0.48170000314712524},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.4350000023841858}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7678999900817871},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.7153000235557556},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.7093999981880188},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6201000213623047},{"id":"https://openalex.org/C82578977","wikidata":"https://www.wikidata.org/wiki/Q16773055","display_name":"Data aggregator","level":3,"score":0.5368000268936157},{"id":"https://openalex.org/C70587473","wikidata":"https://www.wikidata.org/wiki/Q7834111","display_name":"Transformative learning","level":2,"score":0.48170000314712524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44179999828338623},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4350999891757965},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.4350000023841858},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40369999408721924},{"id":"https://openalex.org/C2778207910","wikidata":"https://www.wikidata.org/wiki/Q397610","display_name":"Agr\u00e9gation","level":3,"score":0.35120001435279846},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26440000534057617}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.11010","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11010","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":"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.2605.11010","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11010","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":"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":[],"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],"has":[2],"emerged":[3],"as":[4],"a":[5,46],"transformative":[6],"paradigm":[7],"for":[8],"collaborative":[9],"machine":[10],"learning":[11,37],"across":[12,108],"distributed":[13],"environments.":[14],"However,":[15],"its":[16],"performance":[17],"is":[18],"strongly":[19],"influenced":[20],"by":[21],"the":[22,32],"aggregation":[23,54,72,103],"strategy":[24],"used":[25,52],"to":[26,75,118],"combine":[27],"local":[28],"model":[29],"updates":[30],"at":[31],"server,":[33],"which":[34],"directly":[35],"affects":[36],"performance,":[38],"robustness,":[39],"and":[40,59,87,89,96,110,121],"system":[41],"behavior.":[42],"This":[43],"work":[44],"presents":[45],"comprehensive":[47],"experimental":[48],"comparison":[49],"of":[50,78],"widely":[51],"federated":[53],"strategies":[55,104],"under":[56],"both":[57],"homogeneous":[58],"heterogeneous":[60],"data":[61,79,111],"distributions.":[62],"Using":[63],"benchmark":[64],"image":[65],"classification":[66],"datasets,":[67],"we":[68],"analyze":[69],"how":[70],"different":[71],"mechanisms":[73],"respond":[74],"varying":[76,116],"degrees":[77],"heterogeneity,":[80],"examining":[81],"their":[82,114],"impact":[83],"on":[84],"centralized":[85],"accuracy":[86],"loss,":[88],"system-level":[90],"efficiency":[91],"metrics,":[92],"including":[93],"aggregation,":[94],"training,":[95],"communication":[97],"time.":[98],"The":[99],"results":[100],"demonstrate":[101],"that":[102],"exhibit":[105],"distinct":[106],"trade-offs":[107],"datasets":[109],"distributions,":[112],"with":[113],"effectiveness":[115],"according":[117],"dataset":[119],"characteristics":[120],"operating":[122],"conditions.":[123]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-14T00:00:00"}